AI Paper Atlas

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

NeurIPS 2019 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 16 citations (OpenAlex)

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 changedWhereMeasuredEffect
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · FB15KHITS@1 (%): 49.8 -> 96.4Improved
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · FB15KMRR: 0.61 -> 0.96Improved
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · LUBM1U (reasoning)MRR: 0.26 -> 0.46Improved
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · LUBM1U (reasoning)Mean rank: 1292.6 -> 220.1Improved
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · WN18MRR: 0.90 -> 0.71Hurt
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · FB15KMean rank: 68.4 -> 72.0Mixed
use quantum-logic subspace embedding (E2R) instead of TransE/ComplExE2R · FB15K and LUBM1UHITS@10 (%): FB15K 81.2 -> 96.4; LUBM1U 49.1 -> 45.4Mixed
vary embedding dimension d from 100 to 300 (ablation)E2R · FB15K/WN18/LUBM1UaccuracyNo clear effect
use several negative entities per positive in training (ablation)E2R · FB15K/WN18/LUBM1UconvergenceImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy