Difference between revisions of "Dsc:progress"
(→State of the art工作) |
|||
Line 34: | Line 34: | ||
* PyTorch-Biggraph | * PyTorch-Biggraph | ||
− | + | github: https://github.com/facebookresearch/PyTorch-BigGraph | |
− | + | 教程: https://ai.facebook.com/blog/open-sourcing-pytorch-biggraph-for-faster-embeddings-of-extremely-large-graphs/?source=post_page | |
+ | 手册: https://torchbiggraph.readthedocs.io/en/latest/ | ||
* PS-Graph | * PS-Graph | ||
Line 43: | Line 44: | ||
* DGL-KE | * DGL-KE | ||
github: | github: | ||
− | + | 教程: https://towardsdatascience.com/optimize-knowledge-graph-embeddings-with-dgl-ke-1fff4ab275f2 | |
== 工具包 == | == 工具包 == | ||
Line 54: | Line 55: | ||
* TorchKGE | * TorchKGE | ||
+ | github: https://github.com/torchkge-team/torchkge. | ||
* DGL | * DGL | ||
− | + | github: https://github.com/dmlc/dgl | |
== 国内外相关课题组 == | == 国内外相关课题组 == | ||
− | # 北京大学 崔斌教授组 | + | # 北京大学 崔斌教授组 : [http://net.pku.edu.cn/~cuibin/cuibin_cn.html 主页链接] |
== 研究报告 == | == 研究报告 == |
Revision as of 08:06, 25 January 2021
Contents
研究目标
- 基于PyTorch底层API,设计容纳翻译模型(Trans系列)的分布式表示学习算法,以支持大规模知识图谱分布式表示学习
- 权衡计算通信代价,优化训练过程,在准确率不降低(或少量降低)的前提下,减少训练时间,提升效率
- 在真实知识图谱(DBpedia,Wikidata等)上进行对比实验,验证算法的准确性、高效性和可扩展性
相关论文
综述:
模型:
- Translating Embeddings for Modeling Multi-relational Data (NIPS 2013)
- Knowledge Graph Embedding by Translating on Hyperplanes (AAAI 2014)
- Learning Entity and Relation Embeddings for Knowledge Graph Completion (AAAI 2015)
- Knowledge Graph Embedding via Dynamic Mapping Matrix (IJCNLP 2015)
- Differentiating Concepts and Instances for Knowledge Graph Embedding (EMNLP 2018)
系统:
- Scaling Distributed Machine Learning with the Parameter Server (OSDI 2014)
- 可扩展机器学习的并行与分布式优化算法综述 (软件学报 2017)
- Angel: a new large-scale machine learning system (National Science Review 2018)
- PYTORCH-BIGGRAPH: A LARGE-SCALE GRAPH EMBEDDING SYSTEM (SysML 2019)
- PSGraph: How Tencent trains extremely large-scale graphs with Spark? (ICDE 2020)
- AliGraph: A Comprehensive Graph Neural Network Platform (KDD 2019)
- PyTorch Distributed: Experiences on Accelerating Data Parallel Training (VLDB 2020)
- 图嵌入算法分布式优化 (软件学报 2020)
- EDGES: An Efficient Distributed Graph Embedding System on GPU clusters (TPDS 2020)
- DGL-KE: Training Knowledge Graph Embeddings at Scale (SIGIR 2020)
- TORCHKGE: KNOWLEDGE GRAPH EMBEDDING IN PYTHON AND PYTORCH (Arxiv 2020)
State of the art工作
- PyTorch-Biggraph
github: https://github.com/facebookresearch/PyTorch-BigGraph 教程: https://ai.facebook.com/blog/open-sourcing-pytorch-biggraph-for-faster-embeddings-of-extremely-large-graphs/?source=post_page 手册: https://torchbiggraph.readthedocs.io/en/latest/
- PS-Graph
- AliGraph
- DGL-KE
github: 教程: https://towardsdatascience.com/optimize-knowledge-graph-embeddings-with-dgl-ke-1fff4ab275f2
工具包
- PyTorch
教程:https://pytorch.org/tutorials/beginner/dist_overview.html
- OpenKE
- TorchKGE
github: https://github.com/torchkge-team/torchkge.
- DGL
github: https://github.com/dmlc/dgl
国内外相关课题组
- 北京大学 崔斌教授组 : 主页链接