RulE: Knowledge Graph Reasoning with Rule Embedding
Xiaojuan Tang, Song-Chun Zhu, Yitao Liang, Muhan Zhang

TL;DR
RulE introduces a unified rule embedding framework for knowledge graph reasoning, combining logical rules and entity-relation embeddings to improve inference accuracy and robustness.
Contribution
The paper presents a novel method that jointly learns rule and entity embeddings, enabling soft logical inference and improved knowledge graph reasoning.
Findings
Outperforms existing embedding and rule-based methods on benchmarks.
Effectively integrates logical rules into embedding space.
Enhances KG reasoning with a simple yet effective approach.
Abstract
Knowledge graph (KG) reasoning is an important problem for knowledge graphs. In this paper, we propose a novel and principled framework called \textbf{RulE} (stands for {Rul}e {E}mbedding) to effectively leverage logical rules to enhance KG reasoning. Unlike knowledge graph embedding (KGE) methods, RulE learns rule embeddings from existing triplets and first-order {rules} by jointly representing \textbf{entities}, \textbf{relations} and \textbf{logical rules} in a unified embedding space. Based on the learned rule embeddings, a confidence score can be calculated for each rule, reflecting its consistency with the observed triplets. This allows us to perform logical rule inference in a soft way, thus alleviating the brittleness of logic. On the other hand, RulE injects prior logical rule information into the embedding space, enriching and regularizing the entity/relation embeddings. This…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsAdvanced Graph Neural Networks · Topic Modeling · Bayesian Modeling and Causal Inference
