Multi-view Privileged Information-based Representation Learning for Liver Cancer Diagnosis

Bangming Gong, Huo Yan
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:942-957, 2025.

Abstract

Privileged information (PI) provides additional knowledge to improve performance. Though some efforts are carried out by learning using privileged information (LUPI), they mainly focus on classifier-level LUPI and single-view PI tasks. Therefore, it is a challenge for feature representation learning by transferring multi-view PI to improve the main view. In this paper, we propose a novel feature-level LUPI for multi-view PI tasks, called the multi-view privileged information-based representation learning (MPIRL) algorithm, in which multi-view PI and main view are required at the training phase, but only the main view is available at the testing phase. MPIRL consists of a feature-level LUPI module and a classification module. The feature-level LUPI module of MPIRL designs a multi-branch structure to transfer the multi-view privileged information to the main view, so that diversity and discriminative representation can be generated. For the classification module, multi-view deep SVM (MDSVM) is developed, which combines a multi-channel deep neural network with SVM into a unified framework. MDSVM further learns the fusion representation and classification simultaneously to improve the generalization performance. The experimental results on the dual-view PI tasks and multi-view PI tasks of the real-world multi-view liver cancer dataset show that the proposed MPIRL achieves superior performance with an accuracy of 86.92%, sensitivity of 89.58%, and specificity of 84.25%.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-gong25a, title = {Multi-view Privileged Information-based Representation Learning for Liver Cancer Diagnosis}, author = {Gong, Bangming and Yan, Huo}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {942--957}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/gong25a/gong25a.pdf}, url = {https://proceedings.mlr.press/v304/gong25a.html}, abstract = {Privileged information (PI) provides additional knowledge to improve performance. Though some efforts are carried out by learning using privileged information (LUPI), they mainly focus on classifier-level LUPI and single-view PI tasks. Therefore, it is a challenge for feature representation learning by transferring multi-view PI to improve the main view. In this paper, we propose a novel feature-level LUPI for multi-view PI tasks, called the multi-view privileged information-based representation learning (MPIRL) algorithm, in which multi-view PI and main view are required at the training phase, but only the main view is available at the testing phase. MPIRL consists of a feature-level LUPI module and a classification module. The feature-level LUPI module of MPIRL designs a multi-branch structure to transfer the multi-view privileged information to the main view, so that diversity and discriminative representation can be generated. For the classification module, multi-view deep SVM (MDSVM) is developed, which combines a multi-channel deep neural network with SVM into a unified framework. MDSVM further learns the fusion representation and classification simultaneously to improve the generalization performance. The experimental results on the dual-view PI tasks and multi-view PI tasks of the real-world multi-view liver cancer dataset show that the proposed MPIRL achieves superior performance with an accuracy of 86.92%, sensitivity of 89.58%, and specificity of 84.25%.} }
Endnote
%0 Conference Paper %T Multi-view Privileged Information-based Representation Learning for Liver Cancer Diagnosis %A Bangming Gong %A Huo Yan %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-gong25a %I PMLR %P 942--957 %U https://proceedings.mlr.press/v304/gong25a.html %V 304 %X Privileged information (PI) provides additional knowledge to improve performance. Though some efforts are carried out by learning using privileged information (LUPI), they mainly focus on classifier-level LUPI and single-view PI tasks. Therefore, it is a challenge for feature representation learning by transferring multi-view PI to improve the main view. In this paper, we propose a novel feature-level LUPI for multi-view PI tasks, called the multi-view privileged information-based representation learning (MPIRL) algorithm, in which multi-view PI and main view are required at the training phase, but only the main view is available at the testing phase. MPIRL consists of a feature-level LUPI module and a classification module. The feature-level LUPI module of MPIRL designs a multi-branch structure to transfer the multi-view privileged information to the main view, so that diversity and discriminative representation can be generated. For the classification module, multi-view deep SVM (MDSVM) is developed, which combines a multi-channel deep neural network with SVM into a unified framework. MDSVM further learns the fusion representation and classification simultaneously to improve the generalization performance. The experimental results on the dual-view PI tasks and multi-view PI tasks of the real-world multi-view liver cancer dataset show that the proposed MPIRL achieves superior performance with an accuracy of 86.92%, sensitivity of 89.58%, and specificity of 84.25%.
APA
Gong, B. & Yan, H.. (2025). Multi-view Privileged Information-based Representation Learning for Liver Cancer Diagnosis. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:942-957 Available from https://proceedings.mlr.press/v304/gong25a.html.

Related Material