分布式表示学习
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:
- Knowledge Graph Embedding: A Survey of Approaches and Applications (TKDE 2017)
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:
- PYTORCH-BIGGRAPH: A LARGE-SCALE GRAPH EMBEDDING SYSTEM (SysML 2019)
- Angel: a new large-scale machine learning system (National Science Review 2018) : | Angel
State of the art工作
- PyTorch-Biggraph
- PS-Graph
- AliGraph
- DGL-KE
工具包
国内外相关课题组
- 北京大学 崔斌教授组