English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multi-view clustering (MVC) aims at exploring category structures amongmulti-view data in self-supervised manners. Multiple views provide moreinformation than single views and thus existing MVC methods can achievesatisfactory performance. However, their performance might seriously degeneratewhen the views are noisy in practical multi-view scenarios. In this paper, wefirst formally investigate the drawback of noisy views and then propose atheoretically grounded deep MVC method (namely MVCAN) to address this issue.Specifically, we propose a novel MVC objective that enables un-sharedparameters and inconsistent clustering predictions across multiple views toreduce the side effects of noisy views. Furthermore, a two-level multi-viewiterative optimization is designed to generate robust learning targets forrefining individual views' representation learning. Theoretical analysisreveals that MVCAN works by achieving the multi-view consistency,complementarity, and noise robustness. Finally, experiments on extensive publicdatasets demonstrate that MVCAN outperforms state-of-the-art methods and isrobust against the existence of noisy views.

Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios