Knowledge representation learning Those what I have read
- 知识图谱数据管理研究综述;
- 知识表示学习研究进展;
- Knowledge Graph Embedding: A Survey of Approaches and Applications;
- Translating Embeddings for Modeling Multi-relational Data(TransE);
- Knowledge Graph Embedding by Translating on Hyperplanes(TransH);
- Knowledge Graph Embedding via Dynamic Mapping Matrix(TransD);
- Type-Constrained Representation Learning in Knowledge Graphs;
- Representation Learning of Knowledge Graphs with Hierarchical Types(TKRL);
- 融合实体类别信息的知识图谱表示学习方法(TEKRL)
- Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning(IterE忘记了);
- Differentiating Concepts and Instances for Knowledge Graph Embedding(TransC);
- TransRHS: A Representation Learning Method for Knowledge Graphs with Relation Hierarchical Structure;
- TKRL: Representation Learning of Knowledge Graphs with Hierarchical Types(ijcai );
- 融合实体类别信息的知识图谱表示学习方法(TEKRL 软件学报 2020-04);
- AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding(EMNLP 2020);
- KR-EAR: Knowledge Representation Learning with Entities, Attributes and Relations (IJCAI 2016);
- JOIE:Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts (KDD 2019);
- Differentiating Concepts and Instances for Knowledge Graph Embedding(TransC);
- JOIE:Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts (KDD 2019);
- Incorporating Entity Type Information into Knowledge Representation Learning (DSC 2020); ;TPPA is a simple method which uses the Bayes’ possibility theorem to generate a prior possibility of each triplet. Then TPPA replaces the zero possibility of the missing triplet with the generated prior possibility during training KRL models to overcome drawbacks of CWA in link prediction.