AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification

Xiaolong Chen, Fuyuan Xiao, Xiaohong Zhang, Zehong Cao, Chin-teng Lin

ICML 2026 · Label-efficient and robust learning › OOD and anomaly detection · approach: Uncertainty and misclassification detection

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 complex-valued representation instead of real-valued (ablation)TrustworthyQENN · MSTAR (ablation)AUROC: 86.47 -> 90.47Improved
use complex-valued representation instead of real-valued (ablation)TrustworthyQENN · FUSAR-Ship (ablation)AUROC: 75.50 -> 78.01Improved
use complex-valued representation instead of real-valued (ablation)TrustworthyQENN · EuroSAT (ablation)AUROC: 83.00 -> 83.85Improved
add GQECR quantum evidential reasoning (ablation)TrustworthyQENN · FUSAR-Ship (ablation)AUROC: 79.36 -> 82.67Improved
add GQECR quantum evidential reasoning (ablation)TrustworthyQENN · MSTAR (ablation)AUROC: 91.24 -> 95.94Improved
add GQECR quantum evidential reasoning (ablation)TrustworthyQENN · EuroSAT (ablation)AUROC: 84.16 -> 89.53Improved
add JAP-Loss (ablation)TrustworthyQENN · MSTAR (ablation)OSCR: 93.47 -> 95.93Improved
add JAP-Loss (ablation)TrustworthyQENN · FUSAR-Ship (ablation)FPR95: 69.31 -> 66.23Improved
add JAP-Loss (ablation)TrustworthyQENN · EuroSAT (ablation)AUROC: 88.66 -> 89.53Improved
increase ensemble size N from 1 to 10 (ablation)TrustworthyQENN · MSTAR (sensitivity)AUROCImproved
set balance parameter alpha to 0.4 (ablation)TrustworthyQENN · MSTAR (sensitivity)AUROCImproved

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