Research map / Graph learning / Knowledge and temporal graphs
Interpreting Knowledge Graph Relation Representation from Word Embeddings
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 additive-multiplicative MuRE instead of the evaluated alternatives | Knowledge graph link prediction · WN18RR | Hits@10: 0.53 -> 0.57 | Helped |
| Use additive-multiplicative MuRE instead of TransE | Knowledge graph link prediction · WN18RR | Hits@10: 0.38 -> 0.57 | Helped |
| Use multiplicative DistMult for type R relations rather than additive-only models | Knowledge graph link prediction · WN18RR, type R | Hits@10: verb_group: 0.87 -> 0.97; also_see: 0.59 -> 0.67 | Helped |
| Use a model with both multiplicative and additive components for type S/C relations | Knowledge graph link prediction · WN18RR, type S/C | Hits@10: hypernym: 0.19 -> 0.28; has_part: 0.28 -> 0.35 | Helped |
| Use MuRE rather than multiplicative-only models for standalone fact classification | Knowledge graph fact classification · WN18RR | test accuracy: 0.37 -> 0.50 | Helped |
| Increase relation complexity from type R to type S/C | Knowledge graph link prediction models · WN18RR and NELL-995 | Hits@10 | Hurt |
Closest papers by meaning
- SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions (AAAI 2017 · similarity 0.90)
- An Open-World Extension to Knowledge Graph Completion Models (AAAI 2019 · similarity 0.90)
- Contextual Parameter Generation for Knowledge Graph Link Prediction (AAAI 2020 · similarity 0.90)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.89)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.89)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · 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.