Research map / Graph learning / Knowledge and temporal graphs
Faithful Rule Extraction for Differentiable Rule Learning Models
Xiaxia Wang, David Jaime Tena Cucala, Bernardo Cuenca Grau, Ian Horrocks
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a method for extracting rules from differentiable rule learning models over knowledge graphs with formal faithfulness guarantees between the model and the extracted rules.
Problem
Rule extraction from ML models trained on knowledge graph tasks often lacks formal guarantees about how faithfully the extracted rules reflect the model's behaviour.
Approach
Provides formal guarantees establishing the precise relationship between differentiable rule learning models and the rules extracted from them, rather than heuristic extraction.
Closest papers by meaning
- DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs (NeurIPS 2019 · similarity 0.86)
- Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning (AAAI 2025 · similarity 0.86)
- LLM-DR: A Novel LLM-Aided Diffusion Model for Rule Generation on Temporal Knowledge Graphs (AAAI 2025 · similarity 0.85)
- Differentiable Rule Induction from Raw Sequence Inputs (ICLR 2025 · similarity 0.83)
- Understanding Expressivity of GNN in Rule Learning (ICLR 2024 · similarity 0.83)
- Large Language Models are Interpretable Learners (ICLR 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
