Research map / Graph learning / Knowledge and temporal graphs
Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
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 contextual LERP functions to DRUM-style chain rules (ablation) | DRUM-style rule learning · WN18RR | MRR: 0.486 -> 0.622 | Helped |
| Add contextual LERP functions to DRUM-style chain rules (ablation) | DRUM-style rule learning · Family | MRR: 0.958 -> 0.970 | Helped |
| Add contextual LERP functions to DRUM-style chain rules (ablation) | DRUM-style rule learning · Kinship | MRR: 0.534 -> 0.643 | Helped |
| Add contextual LERP functions to DRUM-style chain rules (ablation) | DRUM-style rule learning · UMLS | MRR: 0.695 -> 0.762 | Helped |
| Increase LERP depth from 0 to 1 (ablation) | LERP · Knowledge graph completion | accuracy | Helped |
| Increase LERP width beyond the validation-selected capacity (ablation) | LERP · Knowledge graph completion | test performance | Mixed |
| Increase the number of learned rules (ablation) | LERP · Knowledge graph completion | performance | Helped |
| Add LERP contextual representation to TransE | TransE · Family | test performance | Helped |
| Add entropy regularization to TransE+LERP (ablation) | TransE+LERP · Family | test performance | Helped |
| Use a second model to generate rule parameters (ablation) | DRUM · Family, UMLS, and Kinship | completion score: score_without - score_with ∈ [-0.01, +0.02] | No clear effect |
| Use a second model to generate rule parameters (ablation) | DRUM · Rule-learning training | convergence speed | Helped |
Closest papers by meaning
- Rule-Guided Compositional Representation Learning on Knowledge Graphs (AAAI 2020 · similarity 0.89)
- 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 0.86)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.86)
- Understanding Expressivity of GNN in Rule Learning (ICLR 2024 · similarity 0.86)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.85)
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.