mlsanityData to 7 Oct 2026

Composition-based Multi-Relational Graph Convolutional Networks

arXiv 1911.03082 ↗First posted 8 Nov 2019cs.LG stat.MLcited by 395

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.

Key facts. Cited by 395 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 64; 2022: 84; 2023: 84; 2024: 77; 2025: 58; 2026: 28.

395 papers.

Sort:

By area:

  1. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  2. 2022Graph Neural Networks for Graphs with Heterophily: A Surveycited by 175
  3. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
  4. 2021Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Groundingcited by 106
  5. 2021Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learningcited by 106
  6. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  7. 2021Deep Generative Models in Engineering Design: A Reviewcited by 103
  8. 2021Knowledge Graph Reasoning with Relational Digraphcited by 91
  9. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  10. 2024Position: Graph Foundation Models are Already Herecited by 84
  11. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  12. 2021From Statistical Relational to Neurosymbolic Artificial Intelligence: a Surveycited by 72
38 more
  1. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 71
  2. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  3. 2021Temporal Knowledge Graph Forecasting with Neural ODEcited by 61
  4. 2022Neural-Symbolic Models for Logical Queries on Knowledge Graphscited by 60
  5. 2021TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphscited by 59
  6. 2023FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledgecited by 55
  7. 2023Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generationcited by 54
  8. 2023InGram: Inductive Knowledge Graph Embedding via Relation Graphscited by 50
  9. 2022A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphscited by 49
  10. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  11. 2022Temporal Knowledge Graph Reasoning with Historical Contrastive Learningcited by 42
  12. 2022Knowledge Graph Embedding: A Survey from the Perspective of Representation Spacescited by 41
  13. 2021Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphscited by 39
  14. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  15. 2022Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queriescited by 39
  16. 2022Linkless Link Prediction via Relational Distillationcited by 39
  17. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 39
  18. 2021Edge Representation Learning with Hypergraphscited by 37
  19. 2024KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completioncited by 36
  20. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databasescited by 35
  21. 2023Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Promptingcited by 33
  22. 2022Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completioncited by 32
  23. 2023A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphscited by 32
  24. 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 31
  25. 2024A Survey on Temporal Knowledge Graph: Representation Learning and Applicationscited by 30
  26. 2021Role-Aware Modeling for N-ary Relational Knowledge Basescited by 29
  27. 2022Relational Message Passing for Fully Inductive Knowledge Graph Completioncited by 29
  28. 2022AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoningcited by 28
  29. 2022MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplaciancited by 28
  30. 2022Lifelong Embedding Learning and Transfer for Growing Knowledge Graphscited by 28
  31. 2022Weisfeiler and Leman Go Relationalcited by 28
  32. 2022An Open Challenge for Inductive Link Prediction on Knowledge Graphscited by 26
  33. 2022Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphscited by 26
  34. 2021Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphscited by 25
  35. 2021DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialoguescited by 25
  36. 2022Inductive Logical Query Answering in Knowledge Graphscited by 25
  37. 2024A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoningcited by 25
  38. 2023Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMscited by 24

50 most cited of 395 All 395 (JSON)