mlsanityData to 7 Oct 2026

Generalizing to Unseen Elements: A Survey on Knowledge Extrapolation for Knowledge Graphs

arXiv 2302.01859 ↗First posted 3 Feb 2023cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

Knowledge graphs (KGs) have become valuable knowledge resources in various applications, and knowledge graph embedding (KGE) methods have garnered increasing attention in recent years. However, conventional KGE methods still face challenges when it comes to handling unseen entities or relations during model testing. To address this issue, much effort has been devoted to various fields of KGs. In this paper, we use a set of general terminologies to unify these methods and refer to them collectively as Knowledge Extrapolation. We comprehensively summarize these methods, classified by our proposed taxonomy, and describe their interrelationships. Additionally, we introduce benchmarks and provide comparisons of these methods based on aspects that are not captured by the taxonomy. Finally, we suggest potential directions for future research.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 38 of its 66 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

38 of 66 references.

References · 38

  1. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  2. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  3. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
  4. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 173
  5. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  6. 2021Knowledge Graph Reasoning with Relational Digraphcited by 91
  7. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  8. 2018One-Shot Relational Learning for Knowledge Graphscited by 78
  9. 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
  10. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 71
  11. 2017Open-World Knowledge Graph Completioncited by 64
  12. 2019Few-Shot Knowledge Graph Completioncited by 63
26 more
  1. 2020Relational Message Passing for Knowledge Graph Completioncited by 61
  2. 2020Inductive Entity Representations from Text via Link Predictioncited by 61
  3. 2018Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embeddingcited by 53
  4. 2020Communicative Message Passing for Inductive Relation Reasoningcited by 53
  5. 2021Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphscited by 47
  6. 2020Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Predictioncited by 46
  7. 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
  8. 2020Adaptive Attentional Network for Few-Shot Knowledge Graph Completioncited by 42
  9. 2021Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completioncited by 32
  10. 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 31
  11. 2020Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphscited by 30
  12. 2022Relational Message Passing for Fully Inductive Knowledge Graph Completioncited by 29
  13. 2022Lifelong Embedding Learning and Transfer for Growing Knowledge Graphscited by 28
  14. 2021Inductive Relation Prediction by BERTcited by 27
  15. 2022Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphscited by 26
  16. 2022Inductive Logical Query Answering in Knowledge Graphscited by 25
  17. 2021Cycle Representation Learning for Inductive Relation Predictioncited by 23
  18. 2021Improving Inductive Link Prediction Using Hyper-Relational Factscited by 21
  19. 2022Few-shot Relational Reasoning via Connection Subgraph Pretrainingcited by 18
  20. 2019An Open-World Extension to Knowledge Graph Completion Modelscited by 16
  21. 2022Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in the Federated Settingcited by 15
  22. 2022Disentangled Ontology Embedding for Zero-shot Learningcited by 8
  23. 2022Facing Changes: Continual Entity Alignment for Growing Knowledge Graphscited by 8
  24. 2022Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Informationcited by 8
  25. 2022Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entitiescited by 6
  26. 2021Geometric Models for (Temporally) Attributed Description Logicscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 2; 2025: 2; 2026: 2.

14 papers.

Sort:

By area:

  1. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  2. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
  3. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  4. 2024A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoningcited by 25
  5. 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
  6. 2024A Foundation Model for Zero-shot Logical Query Reasoningcited by 13
  7. 2023TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classificationcited by 9
  8. 2025A Survey of Link Prediction in N-ary Knowledge Graphscited by 4
  9. 2025Inductive Link Prediction on N-ary Relational Facts via Semantic Hypergraph Reasoningcited by 3
  10. 2023Beyond Transduction: A Survey on Inductive, Few Shot, and Zero Shot Link Prediction in Knowledge Graphscited by 2
  11. 2023NeuralKG-ind: A Python Library for Inductive Knowledge Graph Representation Learningcited by 1
  12. 2023Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graphcited by 0
2 more
  1. 2026Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completioncited by 0
  2. 2026Dual-Path LLM Reasoning for Multimodal Few-Shot Knowledge Graph Completioncited by 0