mlsanityData to 7 Oct 2026

Convolutional 2D Knowledge Graph Embeddings

arXiv 1707.01476 ↗First posted 5 Jul 2017cs.LGcited by 729

Not on the map. Why?

Cited by 22 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressive features than deep, multi-layer models -- which potentially limits performance. In this work, we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. We also show that the model is highly parameter efficient, yielding the same performance as DistMult and R-GCN with 8x and 17x fewer parameters. Analysis of our model suggests that it is particularly effective at modelling nodes with high indegree -- which are common in highly-connected, complex knowledge graphs such as Freebase and YAGO3. In addition, it has been noted that the WN18 and FB15k datasets suffer from test set leakage, due to inverse relations from the training set being present in the test set -- however, the extent of this issue has so far not been quantified. We find this problem to be severe: a simple rule-based model can achieve state-of-the-art results on both WN18 and FB15k. To ensure that models are evaluated on datasets where simply exploiting inverse relations cannot yield competitive results, we investigate and validate several commonly used datasets -- deriving robust variants where necessary. We then perform experiments on these robust datasets for our own and several previously proposed models and find that ConvE achieves state-of-the-art Mean Reciprocal Rank across most datasets.

Key facts. Cited by 729 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 142; 2022: 165; 2023: 146; 2024: 128; 2025: 93; 2026: 55.

729 papers.

Sort:

By area:

  1. 2023A Survey of Large Language Modelscited by 2,537
  2. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  3. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  4. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
  5. 2023Large-scale Multi-Modal Pre-trained Models: A Comprehensive Surveycited by 153
  6. 2021Fully Hyperbolic Neural Networkscited by 107
  7. 2021Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learningcited by 106
  8. 2022A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodalcited by 106
  9. 2021Knowledge Graph Reasoning with Relational Digraphcited by 91
  10. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  11. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 83
  12. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
38 more
  1. 2023LLMs4OL: Large Language Models for Ontology Learningcited by 75
  2. 2021NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphscited by 71
  3. 2021TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecastingcited by 67
  4. 2023FactKG: Fact Verification via Reasoning on Knowledge Graphscited by 57
  5. 2021Graph Coarsening with Neural Networkscited by 55
  6. 2022A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphscited by 49
  7. 2021Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphscited by 47
  8. 2022From Discrimination to Generation: Knowledge Graph Completion with Generative Transformercited by 45
  9. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  10. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  11. 2023Exploring Large Language Models for Knowledge Graph Completioncited by 43
  12. 2022Temporal Knowledge Graph Reasoning with Historical Contrastive Learningcited by 42
  13. 2022Knowledge Graph Embedding: A Survey from the Perspective of Representation Spacescited by 41
  14. 2021Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphscited by 39
  15. 2021A Survey on Neural-symbolic Learning Systemscited by 39
  16. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearningcited by 39
  17. 2021Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Conescited by 38
  18. 2022OOD Link Prediction Generalization Capabilities of Message-Passing GNNs in Larger Test Graphscited by 38
  19. 2021Universal Representation Learning of Knowledge Bases by Jointly Embedding Instances and Ontological Conceptscited by 37
  20. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  21. 2023YAGO 4.5: A Large and Clean Knowledge Base with a Rich Taxonomycited by 37
  22. 2021Neuro-Symbolic Inductive Logic Programming with Logical Neural Networkscited by 36
  23. 2024KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completioncited by 36
  24. 2021Continual Learning of Knowledge Graph Embeddingscited by 35
  25. 2021Temporal Knowledge Graph Completion using Box Embeddingscited by 34
  26. 2021Knowledge Enhanced Pretrained Language Models: A Compreshensive Surveycited by 33
  27. 2023Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Promptingcited by 33
  28. 2021Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completioncited by 32
  29. 2022Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completioncited by 32
  30. 2023A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphscited by 32
  31. 2021Meta-Knowledge Transfer for Inductive Knowledge Graph Embeddingcited by 31
  32. 2021EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use casecited by 30
  33. 2022Graph Lifelong Learning: A Surveycited by 30
  34. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  35. 2021Role-Aware Modeling for N-ary Relational Knowledge Basescited by 29
  36. 2021Link Prediction on N-ary Relational Facts: A Graph-based Approachcited by 29
  37. 2022HousE: Knowledge Graph Embedding with Householder Parameterizationcited by 29
  38. 2022Relational Message Passing for Fully Inductive Knowledge Graph Completioncited by 29

50 most cited of 729 All 729 (JSON)