Research map / Graph learning / Knowledge and temporal graphs
Efficient Embeddings of Logical Variables for Query Answering over Incomplete 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 Var2Vec rather than the strongest reported negation-free baseline | complex query answering · NELL995, negation-free queries | MRR (%): 28.8 -> 30.1 | Helped |
| use Var2Vec rather than the strongest reported negation-free baseline | complex query answering · FB15k-237, negation-free queries | MRR (%): 23.2 -> 23.4 | Helped |
| use Var2Vec rather than the strongest reported negation-free baseline | complex query answering · FB15k, negation-free queries | MRR (%): 49.7 -> 51.0 | Helped |
| use Var2Vec rather than the strongest reported baseline supporting negation | complex query answering · NELL995, queries with negation | MRR (%): 7.3 -> 7.5 | Helped |
| use Var2Vec rather than the strongest reported baseline supporting negation | complex query answering · FB15k-237, queries with negation | MRR (%): 6.7 -> 6.4 | Hurt |
| use Var2Vec rather than the strongest reported baseline supporting negation | complex query answering · FB15k, queries with negation | MRR (%): 14.8 -> 18.9 | Helped |
| replace ComplEx with DistMult (ablation) | Var2Vec · NELL995, negation-free queries | MRR (%): 30.1 -> 28.1 | Hurt |
| replace ComplEx with DistMult (ablation) | Var2Vec · FB15k-237, negation-free queries | MRR (%): 23.2 -> 21.6 | Hurt |
| replace ComplEx with DistMult (ablation) | Var2Vec · FB15k, negation-free queries | MRR (%): 51.0 -> 41.8 | Hurt |
| replace product t-norm and t-conorm with Gödel min-max operators (ablation) | Var2Vec · NELL995, negation-free queries | MRR (%): 30.1 -> 25.9 | Hurt |
| replace product t-norm and t-conorm with Gödel min-max operators (ablation) | Var2Vec · FB15k-237, negation-free queries | MRR (%): 23.2 -> 19.4 | Hurt |
| replace product t-norm and t-conorm with Gödel min-max operators (ablation) | Var2Vec · FB15k, negation-free queries | MRR (%): 51.0 -> 45 | Hurt |
Closest papers by meaning
- Complex Query Answering with Neural Link Predictors (ICLR 2021 · similarity 0.94)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.92)
- Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning (AAAI 2025 · similarity 0.88)
- Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning (AAAI 2025 · similarity 0.87)
- An Evaluation of Approaches to Train Embeddings for Logical Inference (Student Abstract) (AAAI 2025 · similarity 0.87)
- A Foundation Model for Zero-shot Logical Query Reasoning (NeurIPS 2024 · 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.