Trusted Multi-View Classification with Expert Knowledge Constraints

Xinyan Liang, Shijie Wang, Yuhua Qian, Qian Guo, Liang Du, Bingbing Jiang, Tingjin Luo, Feijiang Li
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37409-37426, 2025.

Abstract

Multi-view classification (MVC) based on the Dempster-Shafer theory has gained significant recognition for its reliability in safety-critical applications. However, existing methods predominantly focus on providing confidence levels for decision outcomes without explaining the reasoning behind these decisions. Moreover, the reliance on first-order statistical magnitudes of belief masses often inadequately capture the intrinsic uncertainty within the evidence. To address these limitations, we propose a novel framework termed Trusted Multi-view Classification Constrained with Expert Knowledge (TMCEK). TMCEK integrates expert knowledge to enhance feature-level interpretability and introduces a distribution-aware subjective opinion mechanism to derive more reliable and realistic confidence estimates. The theoretical superiority of the proposed uncertainty measure over conventional approaches is rigorously established. Extensive experiments conducted on three multi-view datasets for sleep stage classification demonstrate that TMCEK achieves state-of-the-art performance while offering interpretability at both the feature and decision levels. These results position TMCEK as a robust and interpretable solution for MVC in safety-critical domains. The code is available at https://github.com/jie019/TMCEK_ICML2025.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-liang25p, title = {Trusted Multi-View Classification with Expert Knowledge Constraints}, author = {Liang, Xinyan and Wang, Shijie and Qian, Yuhua and Guo, Qian and Du, Liang and Jiang, Bingbing and Luo, Tingjin and Li, Feijiang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {37409--37426}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/liang25p/liang25p.pdf}, url = {https://proceedings.mlr.press/v267/liang25p.html}, abstract = {Multi-view classification (MVC) based on the Dempster-Shafer theory has gained significant recognition for its reliability in safety-critical applications. However, existing methods predominantly focus on providing confidence levels for decision outcomes without explaining the reasoning behind these decisions. Moreover, the reliance on first-order statistical magnitudes of belief masses often inadequately capture the intrinsic uncertainty within the evidence. To address these limitations, we propose a novel framework termed Trusted Multi-view Classification Constrained with Expert Knowledge (TMCEK). TMCEK integrates expert knowledge to enhance feature-level interpretability and introduces a distribution-aware subjective opinion mechanism to derive more reliable and realistic confidence estimates. The theoretical superiority of the proposed uncertainty measure over conventional approaches is rigorously established. Extensive experiments conducted on three multi-view datasets for sleep stage classification demonstrate that TMCEK achieves state-of-the-art performance while offering interpretability at both the feature and decision levels. These results position TMCEK as a robust and interpretable solution for MVC in safety-critical domains. The code is available at https://github.com/jie019/TMCEK_ICML2025.} }
Endnote
%0 Conference Paper %T Trusted Multi-View Classification with Expert Knowledge Constraints %A Xinyan Liang %A Shijie Wang %A Yuhua Qian %A Qian Guo %A Liang Du %A Bingbing Jiang %A Tingjin Luo %A Feijiang Li %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-liang25p %I PMLR %P 37409--37426 %U https://proceedings.mlr.press/v267/liang25p.html %V 267 %X Multi-view classification (MVC) based on the Dempster-Shafer theory has gained significant recognition for its reliability in safety-critical applications. However, existing methods predominantly focus on providing confidence levels for decision outcomes without explaining the reasoning behind these decisions. Moreover, the reliance on first-order statistical magnitudes of belief masses often inadequately capture the intrinsic uncertainty within the evidence. To address these limitations, we propose a novel framework termed Trusted Multi-view Classification Constrained with Expert Knowledge (TMCEK). TMCEK integrates expert knowledge to enhance feature-level interpretability and introduces a distribution-aware subjective opinion mechanism to derive more reliable and realistic confidence estimates. The theoretical superiority of the proposed uncertainty measure over conventional approaches is rigorously established. Extensive experiments conducted on three multi-view datasets for sleep stage classification demonstrate that TMCEK achieves state-of-the-art performance while offering interpretability at both the feature and decision levels. These results position TMCEK as a robust and interpretable solution for MVC in safety-critical domains. The code is available at https://github.com/jie019/TMCEK_ICML2025.
APA
Liang, X., Wang, S., Qian, Y., Guo, Q., Du, L., Jiang, B., Luo, T. & Li, F.. (2025). Trusted Multi-View Classification with Expert Knowledge Constraints. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:37409-37426 Available from https://proceedings.mlr.press/v267/liang25p.html.

Related Material