analiza aiqbench
This paper introduces ACGRL, a novel framework for multi-view clustering that uses adversarial training to enforce cross-view consistency while eliminating view-identifying information from shared representations. By freezing invariant reference representations derived via gradient reversal, the method effectively disentangles common structural patterns from view-specific details, leading to superior performance on benchmark datasets. The work advances unsupervised learning techniques by addressing a critical challenge in maintaining clustering stability across diverse data perspectives.
Adversarial Consistency-Guided Representation Learning for Multi-view Clustering
arXiv:2609.35212v1 Announce Type: new Abstract: 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.
Abstract: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.
Machine Learning (cs.LG)
arXiv:2609.35212 [cs.LG]
(or arXiv:2609.35212v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.35212 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 220 cuvinte
Subiecte conexe
Phase-Consistent Magnetic Spectral Learning for Multi-View Clustering
arXiv · 27 aug. 2026
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · 13 oct. 2026
AUP Learning Cloud: Streamlining AI Education on AMD
AMD · 6 aug. 2026
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026