mlsanityData to 7 Oct 2026

A Comprehensive Study on Knowledge Graph Embedding over Relational Patterns Based on Rule Learning

arXiv 2308.07889 ↗First posted 15 Aug 2023cs.AI cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Knowledge Graph Embedding (KGE) has proven to be an effective approach to solving the Knowledge Graph Completion (KGC) task. Relational patterns which refer to relations with specific semantics exhibiting graph patterns are an important factor in the performance of KGE models. Though KGE models' capabilities are analyzed over different relational patterns in theory and a rough connection between better relational patterns modeling and better performance of KGC has been built, a comprehensive quantitative analysis on KGE models over relational patterns remains absent so it is uncertain how the theoretical support of KGE to a relational pattern contributes to the performance of triples associated to such a relational pattern. To address this challenge, we evaluate the performance of 7 KGE models over 4 common relational patterns on 2 benchmarks, then conduct an analysis in theory, entity frequency, and part-to-whole three aspects and get some counterintuitive conclusions. Finally, we introduce a training-free method Score-based Patterns Adaptation (SPA) to enhance KGE models' performance over various relational patterns. This approach is simple yet effective and can be applied to KGE models without additional training. Our experimental results demonstrate that our method generally enhances performance over specific relational patterns. Our source code is available from GitHub at https://github.com/zjukg/Comprehensive-Study-over-Relational-Patterns.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 21 of its 46 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

21 of 46 references.

References · 21

  1. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  2. 2016Complex Embeddings for Simple Link Predictioncited by 897
  3. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  4. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  5. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  6. 2019Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Predictioncited by 133
  7. 2019Probabilistic Logic Neural Networks for Reasoningcited by 69
  8. 2020PairRE: Knowledge Graph Embeddings via Paired Relation Vectorscited by 67
  9. 2018Improving Question Answering by Commonsense-Based Pre-Trainingcited by 66
  10. 2019Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoningcited by 63
  11. 2017Knowledge Graph Embedding with Iterative Guidance from Soft Rulescited by 51
  12. 2019Leveraging Knowledge Bases in LSTMs for Improving Machine Readingcited by 37
9 more
  1. 2014Open Question Answering with Weakly Supervised Embedding Modelscited by 26
  2. 2022Knowledge Graph Reasoning with Logics and Embeddings: Survey and Perspectivecited by 18
  3. 2019Rule-Guided Compositional Representation Learning on Knowledge Graphscited by 16
  4. 2022Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learningcited by 12
  5. 2022Ruleformer: Context-aware Differentiable Rule Mining over Knowledge Graphcited by 9
  6. 2022Stay Positive: Knowledge Graph Embedding Without Negative Samplingcited by 5
  7. 2022Instance-based Learning for Knowledge Base Completioncited by 4
  8. 2020A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphscited by 2
  9. 2021Is There More Pattern in Knowledge Graph? Exploring Proximity Pattern for Knowledge Graph Embeddingcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2023PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertipscited by 3
  2. 2024The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Modelscited by 2
  3. 2025Fully Geometric Multi-Hop Reasoning on Knowledge Graphs with Transitive Relationscited by 0