Research map / Graph learning / Knowledge and temporal graphs
SimplE Embedding for Link Prediction in 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 SimplE instead of ComplEx | Knowledge graph link prediction · WN18 | filtered MRR: 0.941 -> 0.942 | Helped |
| Use SimplE instead of ComplEx | Knowledge graph link prediction · FB15k | filtered MRR: 0.692 -> 0.727 | Helped |
| Ignore inverse-relation scores at test time (ablation) | SimplE · WN18 | filtered MRR: 0.942 -> 0.939 | Hurt |
| Ignore inverse-relation scores at test time (ablation) | SimplE · FB15k | filtered MRR: 0.727 -> 0.700 | Hurt |
| Tie relation parameters to encode background rules (ablation) | SimplE on the reduced WN18 training set · WN18 with redundant training triples removed | filtered MRR: 0.384 -> 0.776 | Helped |
| Tie relation parameters to encode background rules (ablation) | SimplE-ignr on the reduced WN18 training set · WN18 with redundant training triples removed | filtered MRR: 0.221 -> 0.772 | Helped |
Closest papers by meaning
- Tensor Decompositions for Temporal Knowledge Base Completion (ICLR 2020 · similarity 0.89)
- Improved Knowledge Graph Embedding Using Background Taxonomic Information (AAAI 2019 · similarity 0.89)
- Complex Embeddings for Simple Link Prediction (ICML 2016 · similarity 0.89)
- You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings (ICLR 2020 · similarity 0.88)
- Relational Pattern Benchmarking on the Knowledge Graph Link Prediction Task (NeurIPS 2021 · similarity 0.88)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (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.