Research map / Graph learning / Knowledge and temporal graphs
Contextual Parameter Generation for Knowledge Graph Link Prediction
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 |
|---|---|---|---|
| generate projection-layer parameters from relation embedding (CoPER) instead of concatenating | ConvE · Kinship | Hits@1: 74.21 -> 83.62 | Helped |
| generate projection-layer parameters from relation embedding (CoPER) | ConvE · NELL-995 | Hits@1: 67.04 -> 72.15 | Helped |
| generate projection-layer parameters from relation embedding (CoPER) | ConvE · UMLS | Hits@1: 92.89 -> 95.46 | Helped |
| generate projection-layer parameters from relation embedding (CoPER) | ConvE · FB15k237 | MRR: 40.51 -> 42.56 | Helped |
| apply CoPER to LSTM and MLP of MINERVA | MINERVA · UMLS, Kinship, FB15k237, NELL-995 | Hits@1: MINERVA 75.3 -> CoPER-MINERVA 77.76 (UMLS) | Helped |
| replace parameter lookup generator with shared g_linear/g_MLP generator (ablation) | CoPER-ConvE · UMLS | Hits@1: 73.82 -> 95.46 | Helped |
| replace parameter lookup generator with g_linear (ablation) | CoPER-ConvE · Kinship | Hits@1: 74.90 -> 83.62 | Helped |
| replace parameter lookup generator with g_linear (ablation) | CoPER-ConvE · WN18RR | Hits@1: 44.10 -> 44.05 | No clear effect |
| replace parameter lookup generator with g_linear (ablation) | CoPER-ConvE · FB15k237 | Hits@1: 30.72 -> 32.18 | Helped |
| use CoPER-ConvE instead of ConvE for convergence | ConvE · five KG datasets | training iterations to reach ConvE best Hits@1: 2.9 to 28.6 times speedup | Helped |
Closest papers by meaning
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.89)
- Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction (AAAI 2024 · similarity 0.88)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.87)
- Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation (Abstract Reprint) (AAAI 2024 · similarity 0.87)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.87)
- Anchoring Path for Inductive Relation Prediction in Knowledge Graphs (AAAI 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.