Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity

Zhou, Shixuan; Xiang, Yi; Qin, Haoxiang; Wang, Haining; Ma, Yukuan; Huang, Han

doi:10.24963/ijcai.2026/604

Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity

Shixuan Zhou, Yi Xiang, Haoxiang Qin, Haining Wang, Yukuan Ma, Han Huang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 5422-5430.

https://doi.org/10.24963/ijcai.2026/604

Keywords

Machine Learning: Feature extraction, selection and dimensionality reduction
Machine Learning: Multi-view learning
Machine Learning: Adversarial machine learning

Abstract

Standard unsupervised multi-view feature selection (UMFS) methods for large datasets exhibit limitations in modeling the competition between cross-view alignment and intra-view diversity, resulting in suboptimal solutions and expensive computational costs. This challenge is exacerbated by the diverse signals inherent in complex samples, which tend to mask shared patterns, thus complicating the pursuit of an optimal trade-off. In this work, we propose a Progressive Adversarial Feature Selection (ProAd-FS) framework for large-scale multi-view learning, which formulates this static trade-off objective as a dynamic competitive process. To be specific, ProAd-FS develops an adversarial decoupled architecture that assigns these competing objectives to distinct inter-view and intra-view games, guided by a robust gated curriculum to prioritize the learning of underlying structures. The entire framework exhibits linear computational complexity in both sample size and feature dimension, and embeds structural sparse regularization for end-to-end optimization. Extensive experimental results show that ProAd-FS achieves state-of-the-art performance while being highly scalable as well, providing an effective solution for large-scale UMFS tasks.

Shixuan Zhou, Yi Xiang, Haoxiang Qin, Haining Wang, Yukuan Ma, and Han Huang. 2026. Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 5422–5430. https://doi.org/10.24963/ijcai.2026/604

@inproceedings{ijcai2026p604,
  title     = {Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity},
  author    = {Zhou, Shixuan and Xiang, Yi and Qin, Haoxiang and Wang, Haining and Ma, Yukuan and Huang, Han},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {5422--5430},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/604},
  url       = {https://doi.org/10.24963/ijcai.2026/604},
}

TY  - CPAPER
TI  - Progressive Adversarial Multi-View Alignment for Unsupervised Embedded Feature Selection with Linear Complexity
AU  - Zhou, Shixuan
AU  - Xiang, Yi
AU  - Qin, Haoxiang
AU  - Wang, Haining
AU  - Ma, Yukuan
AU  - Huang, Han
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 5422
EP  - 5430
DO  - 10.24963/ijcai.2026/604
UR  - https://doi.org/10.24963/ijcai.2026/604
ER  -