Research map / Graph learning / Knowledge and temporal graphs
ER: Equivariance Regularizer for Knowledge Graph Completion
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 ER to RESCAL | RESCAL · WN18RR | MRR: 0.455 -> .499 | Helped |
| Add ER to RESCAL | RESCAL · FB15K-237 | MRR: .353 -> .373 | Helped |
| Add ER to ComplEx | ComplEx · FB15K-237 | MRR: .346 -> .374 | Helped |
| Add ER to RotatE | RotatE · YAGO3-10 | MRR: .495 -> .581 | Helped |
| Use second-order proximity equivariance in addition to first-order proximity equivariance (ablation) | ComplEx · FB15K-237 | MRR | Helped |
| Use first-order proximity equivariance rather than no equivariance regularization (ablation) | ComplEx · FB15K-237 | MRR | Helped |
| Use ER* with a pair-specific similarity parameter instead of ER with a relation-specific parameter (ablation) | ER · Knowledge graph completion benchmarks | performance | No clear effect |
| Use ER with the 3-norm instead of the 2-norm (ablation) | KGC models · Knowledge graph completion benchmarks | performance | No clear effect |
Closest papers by meaning
- Knowledge Graph Completion by Intermediate Variables Regularization (NeurIPS 2024 · similarity 0.90)
- SPAC: Sparse Partitioning and Adaptive Core Tensor Pruning Model for Knowledge Graph Completion (AAAI 2025 · similarity 0.88)
- Modeling Knowledge Graphs with Composite Reasoning (AAAI 2024 · similarity 0.86)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.85)
- KGCRR: An Effective Metric-Driven Knowledge Graph Completion Framework by Designing a Novel Upper Bound Function with Adaptive Approximation to Reciprocal Rank (AAAI 2025 · similarity 0.85)
- Toward a Unified Statistical Theory of Unsupervised Pretraining and Supervised Neural Knowledge Graph Learning (NeurIPS 2026 · similarity 0.85)
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.