http://www.tjudb.cn/dbgroup/api.php?action=feedcontributions&feedformat=atom&user=Liuxin 2026-07-05T21:17:34Z User contributions MediaWiki 1.31.1 http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=933 2020-12-15T16:01:21Z

<p>Liuxin: /* 综述 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> # A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources. ''Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye,Philip S. Yu''. IEEE Transactions on Big Data. [http://shichuan.org/doc/95.pdf paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 融入关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> &lt;!--Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.--&gt;<br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> &lt;!--Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.--&gt;<br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> &lt;!--TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.--&gt;<br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> &lt;!--知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。--&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=932 2020-12-15T16:00:44Z

<p>Liuxin: /* 综述 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> # A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources. ''Xiao Wang, Deyu Bo, Chuan Shi, Shaohua Fan, Yanfang Ye,Philip S. Yu''. IEEE Transactions on Big Data.[http://shichuan.org/doc/95.pdf paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 融入关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> &lt;!--Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.--&gt;<br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> &lt;!--Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.--&gt;<br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> &lt;!--TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.--&gt;<br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> &lt;!--知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。--&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=683 2020-11-11T14:57:04Z

<p>Liuxin: </p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 &amp;nbsp;&amp;nbsp;天津大学二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区 一等奖<br /> # 2018年 “河北省大学生创新创业年会” 一等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛” 一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛” 二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=624 2020-11-11T01:57:01Z

<p>Liuxin: /* 获奖情况 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 &amp;nbsp;&amp;nbsp;天津大学二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区 一等奖<br /> # 2018年 “河北省大学生创新创业年会” 一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区 特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛” 一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛” 二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=623 2020-11-11T01:56:53Z

<p>Liuxin: /* 获奖情况 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 &amp;nbsp;天津大学二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区 一等奖<br /> # 2018年 “河北省大学生创新创业年会” 一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区 特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛” 一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛” 二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=622 2020-11-11T01:56:33Z

<p>Liuxin: /* 获奖情况 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 天津大学二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区 一等奖<br /> # 2018年 “河北省大学生创新创业年会” 一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区 特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛” 一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛” 二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=621 2020-11-11T01:56:21Z

<p>Liuxin: /* 简历 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 天津大学二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区 一等奖<br /> # 2018年 “河北省大学生创新创业年会” 一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区 特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛” 一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛” 二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=614 2020-11-10T17:04:24Z

<p>Liuxin: /* 获奖情况 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 天津大学二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区 一等奖<br /> # 2018年 “河北省大学生创新创业年会” 一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区 特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛” 一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛” 二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=613 2020-11-10T17:01:30Z

<p>Liuxin: </p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> <br /> == 实习经历 ==<br /> 2019.01-2019.08 天津开发区精诺瀚海数据科技有限公司 研发工程师&lt;/br&gt;<br /> 2016.03-2017.06 火星先驱（天津）科技有限公司 前端工程师&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区一等奖<br /> # 2018年 “河北省大学生创新创业年会”一等奖<br /> # 2018年 “创青春全国大学生创业大赛”河北赛区特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛”一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛”二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=610 2020-11-10T16:53:28Z

<p>Liuxin: /* 获奖情况 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区一等奖<br /> # 2018年 “河北省大学生创新创业年会”一等奖<br /> # 2018年 “创青春全国大学生创业大赛”河北赛区特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛”一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛”二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=608 2020-11-10T16:51:06Z

<p>Liuxin: /* 软件著作权 */</p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区一等奖<br /> # 2018年 “河北省大学生创新创业年会”一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛”一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛”二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=607 2020-11-10T16:50:53Z

<p>Liuxin: </p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> <br /> == 获奖情况 ==<br /> # 2019年 二等学业奖学金<br /> # 2018年 “微信小程序应用开发大赛”华北赛区一等奖<br /> # 2018年 “河北省大学生创新创业年会”一等奖<br /> # 2018年 “创青春”全国大学生创业大赛河北赛区特等奖<br /> # 2017年 “华北五省（市、自治区）及港澳台计算机应用大赛”一等奖<br /> # 2016年 “华北五省（市、自治区）及港澳台计算机应用大赛”二等奖<br /> <br /> == 软件著作权 ==<br /> # 河北工业大学大学. 医药文本可视化分析系统. 2018. (登记号：2018SR10868)</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=603 2020-11-10T15:03:29Z

<p>Liuxin: </p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> &lt;!--Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.--&gt;<br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> &lt;!--Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.--&gt;<br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> &lt;!--TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.--&gt;<br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> &lt;!--知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。--&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=602 2020-11-10T15:03:03Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> <br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> <br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> &lt;!--<br /> Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.--&gt;<br /> <br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> &lt;!--Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.--&gt;<br /> <br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> &lt;!--TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.--&gt;<br /> <br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> &lt;!--知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。--&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=601 2020-11-10T15:02:07Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> <br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> <br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> &lt;!--<br /> Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.--&gt;<br /> <br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 201. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> &lt;!--Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.--&gt;<br /> <br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> &lt;!--TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.--&gt;<br /> <br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> &lt;!--知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。--&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=600 2020-11-10T14:58:09Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> <br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> <br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> &gt; Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.<br /> <br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 201. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> &gt; Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.<br /> <br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> &gt; TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.<br /> <br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> &gt; 知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=599 2020-11-10T14:55:52Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> <br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> <br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.<br /> <br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 201. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.<br /> <br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.<br /> <br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> 知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=598 2020-11-10T14:55:00Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> <br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> <br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> - Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.<br /> <br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 201. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> - Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.<br /> <br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> - TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.<br /> <br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> - 知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=597 2020-11-10T14:54:22Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型 ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. arXiv 2015. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 基于关系路径 == <br /> # PTransE: Modeling Relation Paths for Representation Learning of Knowledge Bases. ''Yankai Lin, Zhiyuan Liu, Huanbo Luan, Maosong Sun, Siwei Rao, Song Liu''. EMNLP 2015. [https://arxiv.org/pdf/1506.00379.pdf paper]<br /> # Traversing Knowledge Graphs in Vector Space. ''Kelvin Guu, John Miller, Percy Liang''. EMNLP 2015. [https://arxiv.org/abs/1506.01094 paper]<br /> # Knowledge Graph Embedding with Hierarchical Relation Structure. ''Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He''. ACL 2018. [https://www.aclweb.org/anthology/D18-1358.pdf paper]<br /> # TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure. ''Fuxiang Zhang, Xin Wang, Zhao Li, Jianxin Li''. IJCAI 2020. [https://www.ijcai.org/Proceedings/2020/0413.pdf paper]<br /> <br /> == 实体类型方向 ==<br /> <br /> # Type-Constrained Representation Learning in Knowledge Graphs. ''Denis Krompa, Stephan Baier, Volker Tresp''. The Semantic Web - ISWC 2015. [https://doi.org/10.1007/978-3-319-25007-6_37 paper]<br /> <br /> # TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types. ''Ruobing Xie, Zhiyuan Liu, Maosong Sun''. IJCAI 2016. [http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf paper] [https://github.com/thunlp/TKRL code]<br /> ## Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.<br /> <br /> # KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations. ''Yankai Lin, Zhiyuan Liu, Maosong Sun''. IJCAI 201. [http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf paper] [https://github.com/thunlp/KR-EAR code]<br /> ## Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.<br /> <br /> # Differentiating Concepts and Instances for Knowledge Graph Embedding. ''Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu''. EMNLP 2018. [http://aclweb.org/anthology/DB-1222 paper] [https://github.com/davidlvxin/TransC code]<br /> ## TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.<br /> <br /> # AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding. ''Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li''. EMNLP 2020. [https://arxiv.org/pdf/2009.12030 paper]<br /> ## 知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=592 2020-11-10T14:43:55Z

<p>Liuxin: /* 实体类型方向 */</p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013. [https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型（TransE系列） ==<br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 关系路径方向 ==<br /> <br /> <br /> <br /> == 实体类型方向 ==<br /> <br /> 1. **Type-Constrained Representation Learning in Knowledge Graphs.**<br /> *Denis Krompa, Stephan Baier, Volker Tresp.* The Semantic Web - ISWC 2015. [paper](https://doi.org/10.1007/978-3-319-25007-6_37) <br /> <br /> 1. **TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types.**<br /> *Ruobing Xie, Zhiyuan Liu, Maosong Sun.* IJCAI 2016. [paper](http://www.thunlp.org/~lzy/publications/ijcai2016_tkrl.pdf) [code](https://github.com/thunlp/TKRL)<br /> &gt; Entities should have multiple representations in different types. TKRL is the first attempt to capture the hierarchical types information, which is significant to KRL.<br /> <br /> 1. **KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations.**<br /> *Yankai Lin, Zhiyuan Liu, Maosong Sun.* IJCAI 2016. [paper](http://nlp.csai.tsinghua.edu.cn/~lyk/publications/ijcai2016_krear.pdf) [code](https://github.com/thunlp/KR-EAR) <br /> &gt; Existing KG-relations can be divided into attributes and relations, which exhibit rather distinct characteristics. KG-EAR is a KR model with entities, attributes and relations, which encodes the correlations between entity descriptions.<br /> <br /> 1. **Differentiating Concepts and Instances for Knowledge Graph Embedding.**<br /> *Xin Lv, Lei Hou, Juanzi Li, Zhiyuan Liu.* EMNLP 2018. [paper](http://aclweb.org/anthology/DB-1222) [code](https://github.com/davidlvxin/TransC)<br /> &gt; TransC proposes a novel knowledge graph embedding model by differentiating concepts and instances. Specifically, TransC encodes each concept in knowledge graph as a sphere and each instance as a vector in the same semantic space. This model can also handle the transitivity of isA relations much better than previous models.<br /> <br /> 1. **AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding.**<br /> *Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li.* EMNLP 2020. [paper](https://arxiv.org/pdf/2009.12030)<br /> &gt; 知识图谱表示学习领域的研究，一作是北航的Guanglin Niu。本文将知识图谱中实体-关系-实体的三元组扩展到实体类型-关系-实体类型的类型相关的三元组，提出能够自动化学习实体类型的向量表示的AutoETER模型，并给出建模和推理对称、逆反、传递关系的理论证明，同时能够解决1-N，N-1和N-N这类复杂关系的推理问题。特别的，论文中提出的AutoETER是一个可适配于任意知识图谱表示学习模型的可插播模块，用于提供实体类型表示并进一步提升原有知识图谱表示学习模型的性能。在四个不同数据集上的实验结果表明本文提出的AutoETER方法的有效性和先进性。实验中还给出了可视化分析，可以直观看出实体类型表示的聚类效果明显优于实体表示的聚类效果，说明了实体类型表示的有效性。</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E8%A1%A8%E7%A4%BA%E5%AD%A6%E4%B9%A0%E5%B0%8F%E7%BB%84&diff=587 2020-11-10T14:12:21Z

<p>Liuxin: </p> <hr /> <div><br /> == 综述 ==<br /> # Representation Learning: A Review and New Perspectives. ''Yoshua Bengio, Aaron Courville, and Pascal Vincent''. TPAMI 2013.[https://arxiv.org/pdf/1206.5538.pdf paper]<br /> # 知识表示学习研究进展. ''刘知远，孙茂松，林衍凯，谢若冰''. 计算机研究与发展 2016. [http://crad.ict.ac.cn/CN/article/downloadArticleFile.do?attachType=PDF&amp;id=3099 paper]<br /> # A Review of Relational Machine Learning for Knowledge Graphs. ''Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich''. Proceedings of the IEEE 2016. [https://arxiv.org/pdf/1503.00759.pdf paper]<br /> # Knowledge Graph Embedding: A Survey of Approaches and Applications. ''Quan Wang, Zhendong Mao, Bin Wang, Li Guo''. TKDE 2017. [http://ieeexplore.ieee.org/abstract/document/8047276/ paper]<br /> <br /> == 基于翻译模型（TransE系列） ==<br /> <br /> # TransE: Translating Embeddings for Modeling Multi-relational Data. ''Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko''. NIPS 2013. [http://papers.nips.cc/paper/5071-translating-embeddings-for-modeling-multi-relational-data.pdf paper]<br /> # TransH: Knowledge Graph Embedding by Translating on Hyperplanes. ''Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen''. AAAI 2014. [http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/viewFile/8531/8546 paper]<br /> # TransR &amp; CTransR: Learning Entity and Relation Embeddings for Knowledge Graph Completion. ''Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu''. AAAI 2015. [http://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/download/9571/9523/ paper]<br /> # TransD: Knowledge Graph Embedding via Dynamic Mapping Matrix. ''Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, Jun Zhao''. ACL 2015. [http://anthology.aclweb.org/P/P15/P15-1067.pdf paper]<br /> # TransA: An Adaptive Approach for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Hao Yu, Xiaoyan Zhu''. [https://arxiv.org/pdf/1509.05490.pdf paper]<br /> # TranSparse: Knowledge Graph Completion with Adaptive Sparse Transfer Matrix. ''Guoliang Ji, Kang Liu, Shizhu He, Jun Zhao''. AAAI 2016. [http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/11982/11693 paper]<br /> # TransG: A Generative Mixture Model for Knowledge Graph Embedding. ''Han Xiao, Minlie Huang, Xiaoyan Zhu''. ACL 2016 [http://www.aclweb.org/anthology/P16-1219 paper]<br /> # KG2E: Learning to Represent Knowledge Graphs with Gaussian Embedding. ''Shizhu He, Kang Liu, Guoliang Ji and Jun Zhao''. CIKM 2015. [https://pdfs.semanticscholar.org/941a/d7796cb67637f88db61e3d37a47ab3a45707.pdf paper]<br /> <br /> == 实体类型方向 ==</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=584 2020-11-10T14:10:05Z

<p>Liuxin: </p> <hr /> <div>[[File:liuxin3.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=File:Liuxin3.jpg&diff=582 2020-11-10T14:09:50Z

<p>Liuxin: </p> <hr /> <div></div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=552 2020-11-09T12:58:56Z

<p>Liuxin: </p> <hr /> <div>[[File:liuxin2.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=File:Liuxin2.jpg&diff=551 2020-11-09T12:58:28Z

<p>Liuxin: </p> <hr /> <div></div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=Students&diff=549 2020-11-09T12:53:24Z

<p>Liuxin: /* 2019 */</p> <hr /> <div>{{DISPLAYTITLE:硕士研究生}}<br /> &lt;strong&gt;[[张三 | （样例）创建张三的主页]]&lt;/strong&gt;<br /> <br /> == 2016 ==<br /> <br /> &lt;strong&gt;[[徐强 | 徐强]]&lt;/strong&gt;<br /> <br /> == 2017 ==<br /> <br /> &lt;strong&gt;[[FuxiangZhang | 张富翔]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[王思邈 | 王思邈]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[柴乐乐 | 柴乐乐]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[徐炜淇 | 徐炜淇]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[ZhaoLi | 李钊]]&lt;/strong&gt;<br /> <br /> == 2018 ==<br /> <br /> &lt;strong&gt;[[陈蔚雪 | 陈蔚雪]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[霍正堂 | 霍正堂]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[傅强 | 傅强]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[梁兴亚 | 梁兴亚]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[邢娇 | 邢娇]]&lt;/strong&gt;<br /> <br /> == 2019 ==<br /> <br /> &lt;strong&gt;[[SicongDong | 董思聪]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[刘宝珠 | 刘宝珠]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[申雨鑫| 申雨鑫]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[刘鑫| 刘鑫]]&lt;/strong&gt;<br /> <br /> == 2020 ==</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=File:Liuxin.jpg&diff=545 2020-11-09T12:11:02Z

<p>Liuxin: </p> <hr /> <div></div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=544 2020-11-09T11:59:08Z

<p>Liuxin: </p> <hr /> <div>[[File:liuxin.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=543 2020-11-09T11:58:22Z

<p>Liuxin: </p> <hr /> <div>{{DISPLAYTITLE:刘鑫}}<br /> [[File:liuxin.jpg |140px |thumb|right]]<br /> &lt;big&gt;<br /> 天津大学 国际工程师学院 计算机技术专业 硕士研究生（全日制）<br /> <br /> '''研究方向'''：知识表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300350&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区324室&lt;/br&gt;<br /> '''电子邮箱'''：liuxin_tiei@tju.edu.cn<br /> <br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=Students&diff=542 2020-11-09T11:53:14Z

<p>Liuxin: /* 2019 */</p> <hr /> <div>{{DISPLAYTITLE:硕士研究生}}<br /> &lt;strong&gt;[[张三 | （样例）创建张三的主页]]&lt;/strong&gt;<br /> <br /> == 2016 ==<br /> <br /> &lt;strong&gt;[[徐强 | 徐强]]&lt;/strong&gt;<br /> <br /> == 2017 ==<br /> <br /> &lt;strong&gt;[[FuxiangZhang | 张富翔]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[王思邈 | 王思邈]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[柴乐乐 | 柴乐乐]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[徐炜淇 | 徐炜淇]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[ZhaoLi | 李钊]]&lt;/strong&gt;<br /> <br /> == 2018 ==<br /> <br /> &lt;strong&gt;[[陈蔚雪 | 陈蔚雪]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[霍正堂 | 霍正堂]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[傅强 | 傅强]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[梁兴亚 | 梁兴亚]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[邢娇 | 邢娇]]&lt;/strong&gt;<br /> <br /> == 2019 ==<br /> <br /> &lt;strong&gt;[[SicongDong | 董思聪]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[刘宝珠 | 刘宝珠]]&lt;/strong&gt;<br /> <br /> &lt;strong&gt;[[刘鑫| 刘鑫]]&lt;/strong&gt;<br /> <br /> == 2020 ==</div>

Liuxin http://www.tjudb.cn/dbgroup/index.php?title=%E5%88%98%E9%91%AB&diff=534 2020-11-09T08:16:34Z

<p>Liuxin: Created page with &quot; &lt;big&gt; 天津大学 求是学部 国际工程师学院 硕士研究生 '''研究方向'''：知识图谱表示学习&lt;/br&gt; '''通讯地址'''：天津市津南区海河教育...&quot;</p> <hr /> <div><br /> &lt;big&gt;<br /> 天津大学 求是学部 国际工程师学院 硕士研究生<br /> <br /> '''研究方向'''：知识图谱表示学习&lt;/br&gt;<br /> '''通讯地址'''：天津市津南区海河教育园区雅观路135号 天津大学 北洋园校区 智能与计算学部&lt;/br&gt;<br /> '''邮政编码'''：300354&lt;/br&gt;<br /> '''办公地址'''：55教学楼B区326室&lt;/br&gt;<br /> <br /> 电子邮箱：liuxin_tiei@tju.edu.cn<br /> &lt;/big&gt;<br /> == 简历 ==<br /> 2019年6月于河北工业大学获得工学学士（网络工程）学位。&lt;/br&gt;<br /> 2019年9月至今 天津大学国际工程师学院硕士研究生在读。&lt;/br&gt;</div>

Liuxin