Research map / Graph learning / Knowledge and temporal graphs
InGram: Inductive Knowledge Graph Embedding via Relation Graphs
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 |
|---|---|---|---|
| add attention-based aggregation instead of mean aggregation (ablation) | InGram · NL-100 | MRR: 0.259 -> 0.309 | Helped |
| add attention-based aggregation instead of sum aggregation (ablation) | InGram · NL-100 | MRR: 0.049 -> 0.309 | Helped |
| use mean of adjacent relation vectors for entity self-loop instead of a learnable self-loop vector (ablation) | InGram · NL-100 | MRR: 0.133 -> 0.309 | Helped |
| add dynamic re-split of training facts and targets each epoch (ablation) | InGram · NL-100 | MRR: 0.234 -> 0.309 | Helped |
| add dynamic re-split of training facts and targets each epoch (ablation) | InGram · WK-100 | MRR: 0.036 -> 0.107 | Helped |
| add relation representation update via relation graph (ablation) | InGram · FB-100 | MRR: 0.183 -> 0.223 | Helped |
| add affinity binning (B=10 vs B=1) (ablation) | InGram · NL-100 | MRR: 0.209 -> 0.309 | Helped |
| add affinity binning (B=10 vs B=1) (ablation) | InGram · FB-100 | MRR: 0.142 -> 0.223 | Helped |
| InGram vs best baselines with all relations and entities new | InGram · NL-100 | MRR: 0.220 -> 0.309 | Helped |
| InGram vs NBFNet when 25% of triplets have new relations | InGram · FB-25 | MRR: 0.224 -> 0.133 | Hurt |
| InGram vs NodePiece on all-relations-known benchmark | InGram · WN18RR-style inductive (known relations) | MRR: 0.677 -> 0.739 | Helped |
Closest papers by meaning
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.93)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.90)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.89)
- S²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.89)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.88)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.88)
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.