Research map / Graph learning / Knowledge and temporal graphs
Non-Parametric Estimation of Multiple Embeddings for Link Prediction on Dynamic Knowledge 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 |
|---|---|---|---|
| use puTransE (many small random-walk embedding spaces) instead of TransE | TransE · WN18 | Filtered Mean Rank: 251 -> 29 | Helped |
| use puTransE instead of TransE | TransE · WN18 | Filtered Hits@10: 89.2 -> 94.9 | Helped |
| use puTransE instead of best-tuned TransE/TransR | TransE · WN18 | Filtered Hits@1: 10.2 -> 60.0 | Helped |
| use puTransE instead of TransE on dynamic GS26k (all snapshots) | TransE · GS26k Total | Filtered Mean Rank: 3233 -> 43 | Helped |
| use puTransE instead of TransE on small base set | TransE · GS26k Base | Filtered Hits@10: 46.9 -> 43.5 | Hurt |
| use puTransE instead of TransE on GS26k Total | TransE · GS26k Total | Filtered Hits@10: 35.3 -> 40.1 | Helped |
| use puTransE instead of TransE on GS26k Total | TransE · GS26k Total | Training time: ≈2 hrs + 2 hrs -> ≈1hr | Helped |
| increase number of embedding spaces (ablation) | puTransE · WN18 and GS26k | precision | Helped |
| replace semantic and structural triplet selection with random bagging of triplets (ablation) | puTransE · WN18 | Mean Rank: mean rank >> 5k | Hurt |
| randomize hyperparameters per space instead of tuning one global config (ablation) | TransE/TransR · WN18 | Hits@10 (filtered): 34.6 (TransE worst) -> 94.9 | Helped |
Closest papers by meaning
- Locally Adaptive Translation for Knowledge Graph Embedding (AAAI 2016 · similarity 0.90)
- You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings (ICLR 2020 · similarity 0.89)
- TorusE: Knowledge Graph Embedding on a Lie Group (AAAI 2018 · similarity 0.89)
- Learning Representations of Bi-level Knowledge Graphs for Reasoning beyond Link Prediction (AAAI 2023 · similarity 0.89)
- Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding (NeurIPS 2024 · similarity 0.87)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · 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.