Skip to content

Latest commit

 

History

History
127 lines (111 loc) · 13.5 KB

Knowledge Graph Embedding, Learning, Reasoning, Rule Mining, and Path Finding.md

File metadata and controls

127 lines (111 loc) · 13.5 KB
Raw

Knowledge Graph Embedding, Learning, Reasoning, Rule Mining, and Path Finding

📝 Surveys and Summary

Surveys, Tutorials and Experimental Studies

  1. Knowledge graph embedding: A survey of approaches and applications (TKDE 2017)🌟
  2. Knowledge representation learning: A quantitative review (2018) [Code in this paper]
  3. A Comprehensive Survey of Knowledge Graph Embeddings with Literals: Techniques and Applications (ESWC 2019) [Paper]
  4. Knowledge Graph Embedding for Link Prediction: A Comparative Analysis [Paper]
  5. Realistic Re-evaluation of Knowledge Graph Completion Methods: An Experimental Study [Paper] (SIGMOD 2020) 🌟
  6. Reasoning on Knowledge Graphs: Symbolic or Neural? (AAAI 2022 Tutorial) [Link]
  7. A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal [Link]
  8. Uniting Large Language Models and Knowledge Graphs for Enhanced Knowledge Representation (Big Data LDN 2023) [Video] 🔥

Summary

  1. Papers, Surveys, and Datasets on Knowledge Graph Embedding (KGE) [GitHub]
  2. Knowledge Graph Reasoning: Recent Advances (Slides) [Link]
  3. KG Embedding Approaches [Link]

Related Reading

  1. Awesome Embeddings [GitHub]
  2. Stanford CS224W - Knowledge Graph Reasoning [Slides]
  3. Random Walk in Node Embeddings (DeepWalk, node2vec, LINE, and GraphSAGE) [Link]

📝 KG Embedding and KG Representation

General Papers

  1. DeepWalk: Online Learning of Social Representations (DeepWalk, KDD 2014) [Code, Slides]
  • Use a sentence embedding model
  1. EventKG: A Multilingual Event-Centric Temporal Knowledge Graph
  • Has time and location info
  • A system that integrates knowledge from different existing KBs
  1. Multilingual Knowledge Graph Embedding for Cross-lingual Knowledge Alignment. [Slides]
  2. SimplE Embedding for Link Prediction in Knowledge Graphs
  3. STransE: a novel embedding model of entities and relationships in knowledge bases (NAACL 2016)
  4. The Role of “Condition”: A Novel Scientific Knowledge Graph Representation and Construction Model [Paper, Presentation] (KDD 2019)
  5. Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Concepts [Paper, Presentation] (KDD 2019)
  6. NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding [PDF] (ICDE 2019) 🌟
  • How to find valuable negative samples efficiently
  1. Entity Integrity, Referential Integrity, and Query Optimization with Embedded Uniqueness Constraints [Paper, short paper] (ICDE 2019) 🌟
  2. AutoSF: Searching Scoring Functions for Knowledge Graph Embedding [Video][Slides][Paper] (ICDE 2020) 🌟
  3. TransN: Heterogeneous Network Representation Learning by Translating Node Embeddings [Video][Slides][Paper] (ICDE 2020) 🌟
  4. Generalized Translation-Based Embedding of Knowledge Graph (TKDE 2020) 🌟
  5. Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding (NeurIPS 2020) [Paper]
  6. DGL-KE: Training Knowledge Graph Embeddings at Scale (SIGIR 2020) [Paper] [Code]
  7. Iterative Entity Alignment via Joint Knowledge Embeddings (IJCAI 2017) [Paper] [Slides]
  8. Representation Learning of Knowledge Graphs with Hierarchical Types (IJCAI 2016) [Paper]
  • relation prediction: predict relations between two given entities, i.e., (h; ?; t).
  1. Modeling Relation Paths for Representation Learning of Knowledge Bases (EMNLP 2015) [Paper] [Code]
  • relation prediction: predict relations between two given entities, i.e., (h; ?; t).
  1. Efficient Knowledge Graph Embedding without Negative Sampling (WWW 2021)
  2. MQuadE: a Unified Model for Knowledge Fact Embedding (WWW 2021)
  3. MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph Embeddings (WWW 2021)
  4. Efficient Relation-Aware Scoring Function Search for Knowledge Graph Embedding (ICDE 2021) 🌟
  5. Simple and automated negative sampling for knowledge graph embedding [Paper] (VLDBJ 2021) 🌟
  6. OntoProtein: Protein Pretraining With Gene Ontology Embedding (ICLR 2022) [Paper] [Github]
  7. How to Turn Your Knowledge Graph Embeddings into Generative Models (NeurIPS 2023) [Paper]

Dynamic Embedding

  1. Dynamic Word Embeddings [Paper]
  2. DYREP: LEARNING REPRESENTATIONS OVER DYNAMIC GRAPHS [ICLR 2019] [Paper]
  3. Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs [Know-Evolve, ICML 2017][Paper][Code (C++)]
  4. Continuous-Time Dynamic Network Embeddings [WWW 2018] [Paper]
  5. Efficiently Embedding Dynamic Knowledge Graphs (2019) [Paper]
  6. Dynamic Heterogeneous Information Network Embedding with Meta-path based Proximity (TKDE 2020) [[https://ieeexplore.ieee.org/document/9091208]] [Github]
  7. ChronoR: Rotation Based Temporal Knowledge Graph Embedding (arxiv 2021 or AAAI 2021?) [Paper]

CNN Based Embedding

  1. A novel embedding model for knowledge base completion based on convolutional neural network (NAACL 2018)
  2. Convolutional 2d knowledge graph embeddings (AAAI 2018)

Graph Based Embedding

  1. Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs (ACL 2019) [Paper]
  • Guide attention to both entity (node) and relation (edge) features in a multi-hop neigh-borhood of a given entity/node
  • This paper discuss that KG embedding models are classified as (1) translational models (which are more widely used and popular, such as TransE), (2) CNN based models, and (3) graph based models.
  1. Modeling Relational Data with Graph Convolutional Networks (ESWC 2018) [Paper]
  • Apply GCN for KG Completion (link prediction), compared with the performance of KG embedding models in the experiment.

Enfficient Emedding

  1. NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs (ICLR 2022) [Paper]
  • Anchor based strategy, to achieve parameter efficiency.
  • Some new works have already use NodePiece in experiments, such as InterHT: Knowledge Graph Embeddings by Interaction between Head and Tail Entities (Arxiv 2022) [Paper]

Related Reading

  1. Neural Subgraph Isomorphism Counting (KDD 2020) [Paper] [Code] 🌟
  2. DFS-based frequent graph pattern extraction to characterize the content of RDF Triple Stores (2010) [Paper]
  3. COMPOSITION-BASED MULTI-RELATIONAL GRAPH CONVOLUTIONAL NETWORKS (ICLR 2020) [Paper] [Code]
  4. Knowledge Embedding Based Graph Convolutional Network (WWW 2021)
  5. Making Large Language Models Perform Better in Knowledge Graph Completion (Arxiv 2024) [Paper]

Downstream Applications

  1. Link Prediction
  • You may refer to the SOTA listed on PaperWithCode, e.g., the exp results on FB15K [Link]
  1. Entity Classification

📝 KG Reasoning

Summary

  1. Knowledge Graph Reasoning Papers [GitHub]

General Papers

  1. Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs (Know-Evolve, ICML 2017)[Paper][Code (C++)]
  2. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (DeepPath, EMNLP 2017) [Code](https://github.com/xwhan/DeepPath Notes: https://zhuanlan.zhihu.com/p/33536026)
  3. Reading and Reasoning with Knowledge Graphs (PhD Thesis of Matthew Gardner) [Thesis]
  • Reasoning, Relation Extraction, Modeling Lexical Semantics
  1. The Vadalog System: Datalog-based Reasoning for Knowledge Graphs (VLDB 2018)[PDF] 🌟
  2. Linguistic Petri Nets Based on Cloud Model Theory for Knowledge Representation and Reasoning (TKDE 2018) 🌟
  3. Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning (WWW 2019)
  4. Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphs (NeurIPS 2020) [Paper and Code]
  5. Query2box: Reasoning Over Knowledge Graphs In Vector Space Using Box Embeddings (ICLR 2020)
  6. Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning (EMNLP 2019)
  7. DIVINE: A Generative Adversarial Imitation Learning Framework for Knowledge Graph Reasoning (EMNLP 2019)
  8. Collaborative Policy Learning for Open Knowledge Graph Reasoning (EMNLP 2019)
  9. Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations (EMNLP 2019) [Paper]
  10. xERTE: Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs (ICLR 2021) [Paper] [Code]
  11. SMORE: KNOWLEDGE GRAPH COMPLETION AND MULTI-HOP REASONING IN MASSIVE KNOWLEDGE GRAPHS (Jure's group, Oct 2021) [Paper]
  12. Knowledge Graph Reasoning with Relational Digraph (arxiv 2022) [Paper]

KG Reasoning for LLM/LLM for KG Reasoning 🔥

  1. REASONING ON GRAPHS: FAITHFUL AND INTERPRETABLE LARGE LANGUAGE MODEL REASONING [Paper] [Discussion]
  2. KG-GPT: A General Framework for Reasoning on Knowledge Graphs Using Large Language Models (EMNLP 2023) [Paper]

📝 Rule Mining and Path Finding in KGs

General Papers

  1. RuDiK: Rule Discovery in Knowledge Bases (VLDB 2018) [PDF, demo] 🌟
  2. Discovering Diversified Paths in Knowledge Bases (VLDB 2018) [PDF, demo] 🌟
  3. Robust Discovery of Positive and Negative Rules in Knowledge Bases (ICDE 2018) [PDF] 🌟
  4. An Embedding-Based Approach to Rule Learning in Knowledge Graphs [Paper] (TKDE 2021) 🌟