mlsanityData to 14 Oct 2026

Simple Rule Injection for ComplEx Embeddings

arXiv 2308.03269 ↗First posted 7 Aug 2023cs.CL cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent works in neural knowledge graph inference attempt to combine logic rules with knowledge graph embeddings to benefit from prior knowledge. However, they usually cannot avoid rule grounding, and injecting a diverse set of rules has still not been thoroughly explored. In this work, we propose InjEx, a mechanism to inject multiple types of rules through simple constraints, which capture definite Horn rules. To start, we theoretically prove that InjEx can inject such rules. Next, to demonstrate that InjEx infuses interpretable prior knowledge into the embedding space, we evaluate InjEx on both the knowledge graph completion (KGC) and few-shot knowledge graph completion (FKGC) settings. Our experimental results reveal that InjEx outperforms both baseline KGC models as well as specialized few-shot models while maintaining its scalability and efficiency.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 50 references that are in the map. First posted on arXiv 7 Aug 2023.

Builds on

27 of 50 references.

References · 27

  1. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 932
  2. 2016Complex Embeddings for Simple Link Predictioncited by 902
  3. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  4. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  5. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 175
  6. 2018Canonical Tensor Decomposition for Knowledge Base Completioncited by 150
  7. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  8. 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
  9. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 118
  10. 2020BoxE: A Box Embedding Model for Knowledge Base Completioncited by 105
  11. 2021Knowledge Graph Reasoning with Relational Digraphcited by 92
  12. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 91
15 more
  1. 2018One-Shot Relational Learning for Knowledge Graphscited by 78
  2. 2019Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphscited by 73
  3. 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
  4. 2019Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoningcited by 63
  5. 2017Knowledge Graph Embedding with Iterative Guidance from Soft Rulescited by 51
  6. 2018Improving Knowledge Graph Embedding Using Simple Constraintscited by 36
  7. 2023Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Promptingcited by 33
  8. 2019Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relationscited by 30
  9. 2019Meta-Graph: Few Shot Link Prediction via Meta Learningcited by 24
  10. 2016Lifted Rule Injection for Relation Embeddingscited by 22
  11. 2022Rethinking Graph Convolutional Networks in Knowledge Graph Completioncited by 20
  12. 2021SAFRAN: An interpretable, rule-based link prediction method outperforming embedding modelscited by 15
  13. 2021Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embeddingcited by 15
  14. 2021Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphscited by 8
  15. 2019Can Graph Neural Networks Help Logic Reasoning?cited by 5

Built on by

Not cited yet.