Research map / Graph learning / Knowledge and temporal graphs
Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion
Kunxun Qi, Jianfeng Du, Hai Wan
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 soft triples to background KG (ablation) | LSTK-TELM · HacRED | MRR: 0.416 -> 0.734 | Improved |
| add soft triples to background KG (ablation) | LSTK-TELM · BioRel | MRR: 0.339 -> 0.600 | Improved |
| add textual copy rules (soft triple for each hard triple) (ablation) | LSTK-TELM · BioRel | MRR: 0.511 -> 0.600 | Improved |
| add textual copy rules (ablation) | LSTK-TELM · HacRED | MRR: 0.710 -> 0.734 | Improved |
| allow textual relations in TE-rules (ablation) | LSTK-TELM · HacRED | MRR: 0.579 -> 0.734 | Improved |
| allow textual relations in TE-rules (ablation) | LSTK-TELM · BioRel | MRR: 0.356 -> 0.600 | Improved |
| add disjunctive atoms in TE-rules (ablation) | LSTK-TELM · DocRED | MRR: 0.453 -> 0.514 | Improved |
| use entailment-probability confidence scores instead of fixed 1.0 (ablation) | LSTK-TELM · BioRel | MRR: 0.574 -> 0.600 | Improved |
| textual entailment model instead of BERT relation extraction for soft triples (ablation) | LSTK-TELM · BioRel | MRR: 0.572 -> 0.600 | Improved |
| add soft triples (LSTK-X dagger) without textual relations in rules | DRUM · HacRED | MRR: 0.387 -> 0.347 | Hurt |
| add soft triples (LSTK-X dagger) without textual relations in rules | NeuralLP · HacRED | MRR: 0.395 -> 0.320 | Hurt |
| allow textual relations in learnt rules (LSTK-X vs LSTK-X dagger) | DRUM · HacRED | MRR: 0.347 -> 0.538 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DRUM — DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs (NeurIPS 2019) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.88)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- Knowledge Graphs Can be Learned with Just Intersection Features (ICML 2024 · similarity 0.87)
- S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.86)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.86)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (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.
