Research map / Graph learning / Knowledge and temporal graphs
Towards Unified Neurosymbolic Reasoning on Knowledge Graphs
Qika Lin, Fangzhi Xu, Hao Lu, Kai He, Rui Mao, Jun Liu, Erik Cambria, Mengling Feng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| combine propositional and FOL reasoning (learned lambda) instead of either alone (ablation) | Tunsr · WN18RR, ICEWS14, ICEWS18 (transductive, interpolation, extrapolation) | performance curves | Improved |
| add FOL rule reasoning to propositional reasoning (ablation) | Tunsr · transductive and interpolation (WN18RR, ICEWS14) | performance curves | Mixed |
| use propositional reasoning instead of FOL reasoning (ablation) | Tunsr · extrapolation ICEWS14 | performance curves | Hurt |
| raise rule length (reasoning iterations) from 2 to 6 (ablation) | Tunsr · WN18RR and FB15k-237 V3 | accuracy | Improved |
| raise rule length beyond 6 (ablation) | Tunsr · WN18RR and FB15k-237 V3 | accuracy | No clear effect |
| use small node-sampling M and edge-selection N (ablation) | Tunsr · ICEWS14 and ICEWS18 extrapolation | Hits@10 | Hurt |
| increase node sampling M beyond 120 (ablation) | Tunsr · ICEWS14 and ICEWS18 extrapolation | Hits@10 | No clear effect |
| compare Tunsr against RED-GNN | Tunsr · WN18RR transductive | Hits@10: 62.40 -> 65.78 | Improved |
| compare Tunsr against TECHS in extrapolation | Tunsr · ICEWS14/ICEWS0515/ICEWS18 extrapolation | Hits@10: 1.37%, 0.96%, and 1.26% gains | Improved |
| compare Tunsr against TeAST on Hits@1 | Tunsr · ICEWS0515 interpolation | Hits@1: 60.40 -> 59.89 | Hurt |
| compare Tunsr against ConGLR in 50-negative ranking | Tunsr · WN18RR V4 (50 negatives) | Hits@10: 92.90 -> 89.27 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DRUM — DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs (NeurIPS 2019) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Neuro-Symbolic Integration for Reasoning and Learning on Knowledge Graphs (AAAI 2024 · similarity 0.89)
- Improving Soft Unification with Knowledge Graph Embedding Methods (ICML 2025 · similarity 0.89)
- Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models (ICML 2025 · similarity 0.88)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.88)
- Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning (AAAI 2025 · similarity 0.88)
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (ICLR 2024 · similarity 0.88)
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.
