Research map / Large language models / Retrieval and knowledge
RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphs
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add embedding-based path scores to RNNLogic (ablation) | RNNLogic · FB15k-237 | MRR: 0.288 -> 0.344 | Helped |
| Add embedding-based path scores to RNNLogic (ablation) | RNNLogic · WN18RR | MRR: 0.455 -> 0.483 | Helped |
| Add embedding-based path scores to RNNLogic (ablation) | RNNLogic · Kinship | MRR: 0.639 -> 0.722 | Helped |
| Add embedding-based path scores to RNNLogic (ablation) | RNNLogic · UMLS | MRR: 0.745 -> 0.842 | Helped |
| Add knowledge graph embeddings to the RNNLogic+ predictor (ablation) | RNNLogic+ · FB15k-237 | MRR: 0.299 -> 0.349 | Helped |
| Add knowledge graph embeddings to the RNNLogic+ predictor (ablation) | RNNLogic+ · WN18RR | MRR: 0.489 -> 0.513 | Helped |
| Optimize the rule generator with EM instead of REINFORCE | RNNLogic w/o emb. · Kinship | MRR: 0.312 -> 0.639 | Helped |
| Optimize the rule generator with EM instead of REINFORCE | RNNLogic w/o emb. · UMLS | MRR: 0.504 -> 0.745 | Helped |
| Use logic-rule reasoning with embeddings rather than the strongest listed embedding baseline | RNNLogic with emb. · FB15k-237 | MRR: 0.37 vs 0.344 | Hurt |
Closest papers by meaning
- Probabilistic Logic Neural Networks for Reasoning (NeurIPS 2019 · similarity 0.89)
- Differentiable Learning of Logical Rules for Knowledge Base Reasoning (NeurIPS 2017 · similarity 0.89)
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks (ICLR 2020 · similarity 0.88)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.87)
- Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning (AAAI 2025 · similarity 0.86)
- Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning (AAAI 2025 · similarity 0.86)
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.