mlsanityData to 7 Oct 2026

Inductive Relation Prediction by Subgraph Reasoning

arXiv 1911.06962 ↗First posted 16 Nov 2019cs.LG cs.AI stat.MLcited by 237

Not on the map. Why?

Abstract (arXiv)

The dominant paradigm for relation prediction in knowledge graphs involves learning and operating on latent representations (i.e., embeddings) of entities and relations. However, these embedding-based methods do not explicitly capture the compositional logical rules underlying the knowledge graph, and they are limited to the transductive setting, where the full set of entities must be known during training. Here, we propose a graph neural network based relation prediction framework, GraIL, that reasons over local subgraph structures and has a strong inductive bias to learn entity-independent relational semantics. Unlike embedding-based models, GraIL is naturally inductive and can generalize to unseen entities and graphs after training. We provide theoretical proof and strong empirical evidence that GraIL can represent a useful subset of first-order logic and show that GraIL outperforms existing rule-induction baselines in the inductive setting. We also demonstrate significant gains obtained by ensembling GraIL with various knowledge graph embedding methods in the transductive setting, highlighting the complementary inductive bias of our method.

Key facts. Cited by 237 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 51; 2023: 63; 2024: 45; 2025: 30; 2026: 23.

237 papers.

Sort:

By area:

  1. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  2. 2022Learning on Large-scale Text-attributed Graphs via Variational Inferencecited by 153
  3. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  4. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  5. 2021Knowledge Graph Reasoning with Relational Digraphcited by 91
  6. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  7. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  8. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  9. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 71
  10. 2023Large Language Models can Learn Rulescited by 66
  11. 2022Neural-Symbolic Models for Logical Queries on Knowledge Graphscited by 60
  12. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
38 more
  1. 2023InGram: Inductive Knowledge Graph Embedding via Relation Graphscited by 50
  2. 2022A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphscited by 49
  3. 2021Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphscited by 47
  4. 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
  5. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  6. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  7. 2021Link Prediction with Persistent Homology: An Interactive Viewcited by 37
  8. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  9. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  10. 2022Language Models as Inductive Reasonerscited by 32
  11. 2023A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphscited by 32
  12. 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 31
  13. 2022Knowledge Base Question Answering by Case-based Reasoning over Subgraphscited by 31
  14. 2022Relational Message Passing for Fully Inductive Knowledge Graph Completioncited by 29
  15. 2023Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentationcited by 29
  16. 2022Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learningcited by 28
  17. 2022AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoningcited by 28
  18. 2022Lifelong Embedding Learning and Transfer for Growing Knowledge Graphscited by 28
  19. 2022Weisfeiler and Leman Go Relationalcited by 28
  20. 2021Inductive Relation Prediction by BERTcited by 27
  21. 2021DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledgecited by 26
  22. 2022An Open Challenge for Inductive Link Prediction on Knowledge Graphscited by 26
  23. 2022Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphscited by 26
  24. 2022Inductive Logical Query Answering in Knowledge Graphscited by 25
  25. 2024A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoningcited by 25
  26. 2023BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphscited by 24
  27. 2023Emerging Drug Interaction Prediction Enabled by Flow-based Graph Neural Network with Biomedical Networkcited by 24
  28. 2021Cycle Representation Learning for Inductive Relation Predictioncited by 23
  29. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
  30. 2023A Multi-Task Perspective for Link Prediction with New Relation Types and Nodescited by 23
  31. 2025TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphscited by 23
  32. 2021Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNscited by 22
  33. 2025How Expressive are Knowledge Graph Foundation Models?cited by 22
  34. 2021Improving Inductive Link Prediction Using Hyper-Relational Factscited by 21
  35. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21
  36. 2022Geodesic Graph Neural Network for Efficient Graph Representation Learningcited by 19
  37. 2024ContextGNN: Beyond Two-Tower Recommendation Systemscited by 19
  38. 2022Few-shot Relational Reasoning via Connection Subgraph Pretrainingcited by 18

50 most cited of 237 All 237 (JSON)