Research map / Large language models / Retrieval and knowledge
Quantum Embedding of Knowledge for Reasoning
Dinesh Garg, Shajith Ikbal, Santosh K. Srivastava, Harit Vishwakarma, Hima Karanam, L Venkata Subramaniam
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · FB15K | HITS@1 (%): 49.8 -> 96.4 | Improved |
| use quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · FB15K | MRR: 0.61 -> 0.96 | Improved |
| use quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · LUBM1U (reasoning) | MRR: 0.26 -> 0.46 | Improved |
| use quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · LUBM1U (reasoning) | Mean rank: 1292.6 -> 220.1 | Improved |
| use quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · WN18 | MRR: 0.90 -> 0.71 | Hurt |
| use quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · FB15K | Mean rank: 68.4 -> 72.0 | Mixed |
| use quantum-logic subspace embedding (E2R) instead of TransE/ComplEx | E2R · FB15K and LUBM1U | HITS@10 (%): FB15K 81.2 -> 96.4; LUBM1U 49.1 -> 45.4 | Mixed |
| vary embedding dimension d from 100 to 300 (ablation) | E2R · FB15K/WN18/LUBM1U | accuracy | No clear effect |
| use several negative entities per positive in training (ablation) | E2R · FB15K/WN18/LUBM1U | convergence | Improved |
Closest papers by meaning
- Inductive Quantum Embedding (NeurIPS 2020 · similarity 0.89)
- Faithful Relational Reasoning with Region-based Embeddings: Expressivity of Convex Coordinate-wise Models (ICML 2026 · similarity 0.87)
- An Evaluation of Approaches to Train Embeddings for Logical Inference (Student Abstract) (AAAI 2025 · similarity 0.85)
- Improving Soft Unification with Knowledge Graph Embedding Methods (ICML 2025 · similarity 0.84)
- Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors (ICLR 2024 · similarity 0.84)
- NestE: Modeling Nested Relational Structures for Knowledge Graph Reasoning (AAAI 2024 · similarity 0.83)
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.
