Research map / Label-efficient and robust learning / Recognition and long-tail
Instance-based Learning for Knowledge Base Completion
Wanyun Cui, Xingran Chen
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 instance-based scoring with translational scoring (CIBLE) | Knowledge base completion models · Kinship | MRR: 0.650 -> 0.728 | Improved |
| Combine instance-based scoring with translational scoring (CIBLE) | Knowledge base completion models · UMLS | MRR: 0.816 -> 0.856 | Improved |
| Combine instance-based scoring with translational scoring (CIBLE) | Knowledge base completion models · FB15k-237 | MRR: 0.284 -> 0.341 | Improved |
| Combine instance-based scoring with translational scoring (CIBLE) | Knowledge base completion models · WN18RR | MRR: 0.394 -> 0.490 | Improved |
| Add relation-aware prototype modeling with TransR rather than TransE (ablation) | CIBLE · FB15k-237 | MRR: 0.286 -> 0.341 | Improved |
| Add relation-aware prototype modeling with TransR rather than TransE (ablation) | CIBLE · WN18RR | MRR: 0.236 -> 0.250 | Improved |
| Add relation matrices to RotatE prototype modeling (ablation) | CIBLE · FB15k-237 | MRR: 0.315 -> 0.341 | Improved |
| Add relation matrices to RotatE prototype modeling (ablation) | CIBLE · WN18RR | MRR: 0.430 -> 0.490 | Improved |
| Use IBL rules rather than non-IBL rules only (ablation) | RNNLogic · FB15k-237 | MRR: 0.317 -> 0.326 | Improved |
| Use IBL rules rather than non-IBL rules only (ablation) | RNNLogic · WN18RR | MRR: 44.1 -> 44.0 | No clear effect |
| Use IBL rules rather than non-IBL rules only (ablation) | RNNLogic · Kinship | MRR: 0.667 -> 0.840 | Improved |
| Use IBL rules rather than non-IBL rules only (ablation) | RNNLogic · UMLS | MRR: 0.681 -> 72.1 | Improved |
Closest papers by meaning
- Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement (ICLR 2024 · similarity 0.84)
- From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When (NeurIPS 2024 · similarity 0.83)
- Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens (ICLR 2026 · similarity 0.83)
- RuAG: Learned-rule-augmented Generation for Large Language Models (ICLR 2025 · similarity 0.83)
- Hypothesis Search: Inductive Reasoning with Language Models (ICLR 2024 · similarity 0.83)
- Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective (ICML 2025 · similarity 0.82)
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.
