Research map / Graph learning / Knowledge and temporal graphs
Fuzzy Logic Based Logical Query Answering 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 |
|---|---|---|---|
| Use fuzzy-logic query operators with FuzzQE instead of the strongest query-embedding baseline | FuzzQE · FB15k-237 test EPFO queries | Avg EPFO MRR (%): 20.9 -> 24.2; 3.3% | Helped |
| Use fuzzy-logic query operators with FuzzQE instead of the strongest query-embedding baseline | FuzzQE · NELL995 test EPFO queries | Avg EPFO MRR (%): 24.6 -> 29.3; 4.7% | Helped |
| Use FuzzQE's fuzzy negation operator instead of BetaE's negation operator | FuzzQE · FB15k-237 queries containing negation | Avg Neg MRR (%): 5.5 -> 8.5; 3.0% | Helped |
| Use FuzzQE's fuzzy negation operator instead of BetaE's negation operator | FuzzQE · NELL995 queries containing negation | Avg Neg MRR (%): 5.9 -> 8.0; 2.1% | Helped |
| Use FuzzQE instead of CQD | FuzzQE · FB15k-237 test EPFO queries | Avg EPFO MRR (%): 21.7 -> 24.2; 2.5% | Helped |
| Use FuzzQE instead of CQD | FuzzQE · NELL995 test EPFO queries | Avg EPFO MRR (%): 28.4 -> 29.3; 0.9% | Helped |
| Train FuzzQE with link prediction only rather than adding complex FOL query training data | FuzzQE · FB15k-237 test EPFO queries | Avg EPFO MRR (%): 17.7 -> 21.8; 3.6% | Helped |
| Train FuzzQE with link prediction only rather than adding complex FOL query training data | FuzzQE · NELL995 test EPFO queries | Avg EPFO MRR (%): 21.7 -> 27.1; 5.4% | Helped |
Closest papers by meaning
- NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge Graphs (AAAI 2023 · similarity 0.93)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.91)
- Neural-Symbolic Models for Logical Queries on Knowledge Graphs (ICML 2022 · similarity 0.91)
- A Foundation Model for Zero-shot Logical Query Reasoning (NeurIPS 2024 · similarity 0.89)
- Is Complex Query Answering Really Complex? (ICML 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.