Research map / Graph learning / Knowledge and temporal graphs
ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion
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 Base ExpressivE with learned relation widths rather than setting widths to zero (ablation) | ExpressivE · WN18RR | MRR: .482 -> .508 | Helped |
| Set relation widths to zero, removing spatial capabilities (ablation) | ExpressivE · FB15k-237 | MRR: .333 -> .350 | Helped |
| Allow relation-specific slope vectors instead of tying all slopes (ablation) | ExpressivE · WN18RR | MRR: .353 -> .508 | Helped |
| Allow relation-specific slope vectors instead of tying all slopes (ablation) | ExpressivE · FB15k-237 | MRR: .328 -> .333 | Helped |
| Add relation center vectors (ablation) | ExpressivE · WN18RR | MRR: .501 -> .508 | Helped |
| Add relation center vectors (ablation) | ExpressivE · FB15k-237 | MRR: .314 -> .333 | Helped |
| Represent each relation with two bands rather than one (ablation) | ExpressivE · WN18RR | MRR: .470 -> .508 | Helped |
| Represent each relation with two bands rather than one (ablation) | ExpressivE · FB15k-237 | MRR: .318 -> .333 | Helped |
| Use Base ExpressivE instead of ComplEx | KGC models · WN18RR | MRR: .475 -> .508 | Helped |
| Use Functional ExpressivE instead of TuckER | KGC models · FB15k-237 | MRR: .358 -> .350 | Hurt |
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank (AAAI 2025 · similarity 0.87)
- How Expressive are Knowledge Graph Foundation Models? (ICML 2025 · similarity 0.87)
- KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge (NeurIPS 2024 · similarity 0.87)
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.