Research map / Graph learning / Knowledge and temporal graphs
Data-Dependent Learning of Symmetric/Antisymmetric Relations for Knowledge Base 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 |
|---|---|---|---|
| Replace standard L1 with multiplicative L1 regularization (ablation) | ComplEx · FB15k | filtered MRR: 71.1 -> 73.3 | Helped |
| Replace standard L1 with multiplicative L1 regularization (ablation) | ComplEx · WN18 | filtered MRR: 94.3 -> 94.3 | No clear effect |
| Replace standard L1 with multiplicative L1 regularization (ablation) | ComplEx · synthetic symmetric relations | classification accuracy: 89.8 -> 93.5 | Helped |
| Replace standard L1 with multiplicative L1 regularization (ablation) | ComplEx · synthetic antisymmetric relations | classification accuracy: 92.1 -> 94.4 | Helped |
| Replace standard L1 with multiplicative L1 regularization (ablation) | ComplEx · synthetic other relations | classification accuracy: 65.7 -> 65.3 | Hurt |
| Replace standard L1 with multiplicative L1 regularization (ablation) | ComplEx · synthetic test set, all relations | classification accuracy: 81.5 -> 83.3 | Helped |
| Reduce WN18 training data to half and use multiplicative L1 instead of no L1 regularizer (ablation) | ComplEx · WN18 with half training data | filtered MRR: 48.3 -> 49.0 | Helped |
| Reduce WN18 training data to half and use multiplicative L1 instead of standard L1 regularizer (ablation) | ComplEx · WN18 with half training data | filtered MRR: 48.2 -> 49.0 | Helped |
| Set α to 0, removing the multiplicative L1 contribution (ablation) | ComplEx w/ mul L1 · WN18 | filtered MRR: 94.3 -> 94.3 | No clear effect |
Closest papers by meaning
- On Completing Sparse Knowledge Base with Transitive Relation Embedding (AAAI 2019 · similarity 0.89)
- LENA: Locality-Expanded Neural Embedding for Knowledge Base Completion (AAAI 2019 · similarity 0.89)
- Towards Global-Topology Relation Graph for Inductive Knowledge Graph Completion (AAAI 2025 · similarity 0.87)
- Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion (AAAI 2025 · similarity 0.86)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.86)
- KGDM: A Diffusion Model to Capture Multiple Relation Semantics for Knowledge Graph Embedding (AAAI 2024 · similarity 0.86)
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.