Research map / Graph learning / Knowledge and temporal graphs
Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints
Jiaxin Bai, Xin Liu, Weiqi Wang, Chen Luo, Yangqiu Song
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 |
|---|---|---|---|
| Add MEQE memory module | GQE · CEQA ASER-50K, average over constraint types | Hit@1: 9.12 -> 10.45 | Improved |
| Add MEQE memory module | Q2P · CEQA ASER-50K, average over constraint types | Hit@1: 14.31 -> 15.61 | Improved |
| Add MEQE memory module | Neural MLP · CEQA ASER-50K, average over constraint types | Hit@1: 13.24 -> 15.58 | Improved |
| Add MEQE memory module | FuzzQE · CEQA ASER-50K, average over constraint types | Hit@1: 11.68 -> 15.03 | Improved |
| Add MEQE memory module | FuzzQE · CEQA ASER-50K, average over constraint types | MRR: 16.80 -> 19.47 | Improved |
| Add MEQE memory module | Q2P · CEQA ASER-50K, average over constraint types | Hit@3: 19.83 -> 20.74 | Improved |
| Remove implicit constraints from MEQE memory (ablation) | MEQE on GQE · CEQA ASER-50K, average over constraint types | MRR: 11.90 -> 14.41 | Improved |
| Remove implicit constraints from MEQE memory (ablation) | MEQE on Q2P · CEQA ASER-50K, average over constraint types | MRR: 18.82 -> 19.56 | No clear effect |
| Remove implicit constraints from MEQE memory (ablation) | MEQE on FuzzQE · CEQA ASER-50K, average over constraint types | Hit@1: 13.11 -> 15.03 | Improved |
| Remove feed-forward network from MEQE (ablation) | MEQE on GQE · CEQA ASER-50K, average over constraint types | Hit@1: 0.70 -> 10.45 | Improved |
| Remove feed-forward network from MEQE (ablation) | MEQE on Q2P · CEQA ASER-50K, average over constraint types | MRR: 15.32 -> 19.56 | Improved |
| Remove feed-forward network from MEQE (ablation) | MEQE on FuzzQE · CEQA ASER-50K, average over constraint types | MRR: 14.66 -> 19.47 | Improved |
Closest papers by meaning
- Logical Message Passing Networks with One-hop Inference on Atomic Formulas (ICLR 2023 · similarity 0.88)
- Neural-Symbolic Entangled Framework for Complex Query Answering (NeurIPS 2022 · similarity 0.88)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.87)
- Is Complex Query Answering Really Complex? (ICML 2025 · similarity 0.87)
- A Foundation Model for Zero-shot Logical Query Reasoning (NeurIPS 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.
