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
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:17641-17664, 2026.

Abstract

Out-of-distribution (OOD) detection requires accurately classifying in-distribution (ID) samples while effectively distinguishing anomalous OOD data. However, existing methodologies predominantly rely on real-valued magnitude features, neglecting the semantic richness embedded in phase information, and often lack a systematic theoretical framework for quantitatively modeling uncertainty. To address this dual limitation of incomplete feature representation and insufficient uncertainty modeling, the trustworthy quantum evidence neural network (TrustworthyQENN) is proposed, a novel quantum-inspired framework bridging complex-valued representation learning under the framework of generalized quantum evidence theory (GQET). Specifically, supervised complex-valued contrastive learning (SCVCL) is proposed to synchronize amplitude distributions with phase correlations, thereby enforcing high intra-class compactness and inter-class separability for ID data. A quantum evidence generation mechanism based on GQET is subsequently devised, where the OOD state is formally grounded in the generalized quantum basic probability amplitudes (GQBPAs) within a Hilbert space. Furthermore, the generalized quantum evidential combination rule (GQECR) is leveraged to fuse multi-view quantum evidence, thereby achieving trustworthy inference. Extensive experiments on the MSTAR, EuroSAT, and FUSAR-Ship benchmarks substantiate the superiority of TrustworthyQENN, which achieves a peak AUROC of 95.94% on the MSTAR dataset while consistently outperforming state-of-the-art methods across all evaluated scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-chen26fh, title = {{T}rustworthy{QENN}: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification}, author = {Chen, Xiaolong and Xiao, Fuyuan and Zhang, Xiaohong and Cao, Zehong and Lin, Chin-Teng}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {17641--17664}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/chen26fh/chen26fh.pdf}, url = {https://proceedings.mlr.press/v306/chen26fh.html}, abstract = {Out-of-distribution (OOD) detection requires accurately classifying in-distribution (ID) samples while effectively distinguishing anomalous OOD data. However, existing methodologies predominantly rely on real-valued magnitude features, neglecting the semantic richness embedded in phase information, and often lack a systematic theoretical framework for quantitatively modeling uncertainty. To address this dual limitation of incomplete feature representation and insufficient uncertainty modeling, the trustworthy quantum evidence neural network (TrustworthyQENN) is proposed, a novel quantum-inspired framework bridging complex-valued representation learning under the framework of generalized quantum evidence theory (GQET). Specifically, supervised complex-valued contrastive learning (SCVCL) is proposed to synchronize amplitude distributions with phase correlations, thereby enforcing high intra-class compactness and inter-class separability for ID data. A quantum evidence generation mechanism based on GQET is subsequently devised, where the OOD state is formally grounded in the generalized quantum basic probability amplitudes (GQBPAs) within a Hilbert space. Furthermore, the generalized quantum evidential combination rule (GQECR) is leveraged to fuse multi-view quantum evidence, thereby achieving trustworthy inference. Extensive experiments on the MSTAR, EuroSAT, and FUSAR-Ship benchmarks substantiate the superiority of TrustworthyQENN, which achieves a peak AUROC of 95.94% on the MSTAR dataset while consistently outperforming state-of-the-art methods across all evaluated scenarios.} }
Endnote
%0 Conference Paper %T TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification %A Xiaolong Chen %A Fuyuan Xiao %A Xiaohong Zhang %A Zehong Cao %A Chin-Teng Lin %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-chen26fh %I PMLR %P 17641--17664 %U https://proceedings.mlr.press/v306/chen26fh.html %V 306 %X Out-of-distribution (OOD) detection requires accurately classifying in-distribution (ID) samples while effectively distinguishing anomalous OOD data. However, existing methodologies predominantly rely on real-valued magnitude features, neglecting the semantic richness embedded in phase information, and often lack a systematic theoretical framework for quantitatively modeling uncertainty. To address this dual limitation of incomplete feature representation and insufficient uncertainty modeling, the trustworthy quantum evidence neural network (TrustworthyQENN) is proposed, a novel quantum-inspired framework bridging complex-valued representation learning under the framework of generalized quantum evidence theory (GQET). Specifically, supervised complex-valued contrastive learning (SCVCL) is proposed to synchronize amplitude distributions with phase correlations, thereby enforcing high intra-class compactness and inter-class separability for ID data. A quantum evidence generation mechanism based on GQET is subsequently devised, where the OOD state is formally grounded in the generalized quantum basic probability amplitudes (GQBPAs) within a Hilbert space. Furthermore, the generalized quantum evidential combination rule (GQECR) is leveraged to fuse multi-view quantum evidence, thereby achieving trustworthy inference. Extensive experiments on the MSTAR, EuroSAT, and FUSAR-Ship benchmarks substantiate the superiority of TrustworthyQENN, which achieves a peak AUROC of 95.94% on the MSTAR dataset while consistently outperforming state-of-the-art methods across all evaluated scenarios.
APA
Chen, X., Xiao, F., Zhang, X., Cao, Z. & Lin, C.. (2026). TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:17641-17664 Available from https://proceedings.mlr.press/v306/chen26fh.html.

Related Material