Research map / Graph learning / Knowledge and temporal graphs
Complex Query Answering with Neural Link Predictors
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 CQD-Beam combinatorial search rather than GQE | Complex query answering · FB15k | H@3 Avg: 0.384 -> 0.680 | Helped |
| Use CQD-Beam combinatorial search rather than Query2Box | Complex query answering · FB15k-237 | H@3 Avg: 0.268 -> 0.290 | Helped |
| Use CQD-Beam combinatorial search rather than Query2Box | Complex query answering · NELL995 | H@3 Avg: 0.306 -> 0.375 | Helped |
| Use combinatorial search instead of continuous optimisation | CQD · FB15k | H@3 Avg: 0.576 -> 0.680 | Helped |
| Use combinatorial search instead of continuous optimisation | CQD · FB15k-237 | H@3 Avg: 0.272 -> 0.290 | Helped |
| Use combinatorial search instead of continuous optimisation | CQD · NELL995 | H@3 Avg: 0.368 -> 0.375 | Helped |
| Replace ComplEx with DistMult (ablation) | CQD-Beam · FB15k | H@3 1p: 0.918 -> 0.869 | Hurt |
| Replace ComplEx with DistMult (ablation) | CQD-Beam · FB15k-237 | H@3 1p: 0.512 -> 0.485 | Hurt |
| Replace ComplEx with DistMult (ablation) | CQD-Beam · NELL995 | H@3 1p: 0.667 -> 0.642 | Hurt |
| Reduce embedding rank from 1,000 to 100 (ablation) | CQD-Beam · FB15k | H@3 1p: 0.918 -> 0.893 | Hurt |
| Reduce embedding rank from 1,000 to 100 (ablation) | CQD-Beam · FB15k-237 | H@3 1p: 0.512 -> 0.493 | Hurt |
| Reduce embedding rank from 1,000 to 100 (ablation) | CQD-Beam · NELL995 | H@3 1p: 0.667 -> 0.647 | Hurt |
Closest papers by meaning
- Adapting Neural Link Predictors for Data-Efficient Complex Query Answering (NeurIPS 2023 · similarity 0.95)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.91)
- Is Complex Query Answering Really Complex? (ICML 2025 · similarity 0.87)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.85)
- Reasoning of Large Language Models over Knowledge Graphs with Super-Relations (ICLR 2025 · similarity 0.85)
- Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts (AAAI 2025 · similarity 0.84)
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.