# Adversarial Consistency-Guided Representation Learning for Multi-view Clustering

arXiv: https://arxiv.org/abs/2609.35212 · HTML: https://mlsanity.com/paper/2609.35212/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 21 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Multi-level Feature Learning for Contrastive Multi-view Clustering](https://mlsanity.com/paper/2106.11193/) (2021)
- [Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering](https://mlsanity.com/paper/2106.11232/) (2021)
- [GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clustering](https://mlsanity.com/paper/2305.06799/) (2023)
- [Learning a Self-Expressive Network for Subspace Clustering](https://mlsanity.com/paper/2110.04318/) (2021)
- [DealMVC: Dual Contrastive Calibration for Multi-view Clustering](https://mlsanity.com/paper/2308.09000/) (2023)
- [MetaViewer: Towards A Unified Multi-View Representation](https://mlsanity.com/paper/2303.06329/) (2023)
- [Rethinking Multi-view Representation Learning via Distilled Disentangling](https://mlsanity.com/paper/2403.10897/) (2024)

## Abstract (arXiv)

Multi-view clustering aims to capture cross-view consistency while exploiting view-specific information. However, shared representations learned to capture cross-view consistency may still retain view-identifying information, potentially compromising the consistency of cross-view clustering structures. To address this issue, we propose ACGRL, an adversarial consistency-guided representation learning framework for multi-view clustering. ACGRL employs a gradient-reversal view discriminator to reduce view identifiability and obtain invariant reference representations. These representations are then frozen to provide fixed references for disentangling view-specific information from cross-view common information in the subsequent learning stage. The fixed reference representations are concatenated with the learned view-specific representations for reconstruction and clustering, with cross-view cluster alignment encouraging consistent clustering assignments. Experiments on four benchmark datasets demonstrate the superior clustering performance of ACGRL compared with representative multi-view clustering methods.