URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering

TL;DR

URRL-IMVC introduces a unified, robust embedding learning framework for incomplete multi-view clustering, effectively leveraging multi-view data and handling missing views without explicit recovery, achieving state-of-the-art results.

Contribution

It proposes a novel attention-based auto-encoder with KNN imputation for robust, unified multi-view embeddings in incomplete data scenarios, surpassing existing methods.

Findings

Achieves state-of-the-art clustering performance on benchmark datasets.

Effectively handles view-missing conditions without explicit view recovery.

Validates the robustness and effectiveness through extensive ablation studies.

Abstract

Incomplete multi-view clustering (IMVC) aims to cluster multi-view data that are only partially available. This poses two main challenges: effectively leveraging multi-view information and mitigating the impact of missing views. Prevailing solutions employ cross-view contrastive learning and missing view recovery techniques. However, they either neglect valuable complementary information by focusing only on consensus between views or provide unreliable recovered views due to the absence of supervision. To address these limitations, we propose a novel Unified and Robust Representation Learning for Incomplete Multi-View Clustering (URRL-IMVC). URRL-IMVC directly learns a unified embedding that is robust to view missing conditions by integrating information from multiple views and neighboring samples. Firstly, to overcome the limitations of cross-view contrastive learning, URRL-IMVC incorporates an attention-based auto-encoder framework to fuse multi-view information and generate unified embeddings. Secondly, URRL-IMVC directly enhances the robustness of the unified embedding against view-missing conditions through KNN imputation and data augmentation techniques, eliminating the need for explicit missing view recovery. Finally, incremental improvements are introduced to further enhance the overall performance, such as the Clustering Module and the customization of the Encoder. We extensively evaluate the proposed URRL-IMVC framework on various benchmark datasets, demonstrating its state-of-the-art performance. Furthermore, comprehensive ablation studies are performed to validate the effectiveness of our design.