TY - GEN
T1 - Heterogeneity-Aware Federated Deep Multi-View Clustering towards Diverse Feature Representations
AU - Jiang, Xiaorui
AU - Ma, Zhongyi
AU - Fu, Yulin
AU - Liao, Yong
AU - Zhou, Pengyuan
N1 - Publisher Copyright:
© 2024 ACM.
PY - 2024/10
Y1 - 2024/10
N2 - Multi-view clustering has proven to be highly effective in exploring consistency information across multiple views/modalities when dealing with large-scale unlabeled data. However, in the real world, multi-view data is often distributed across multiple entities, and due to privacy concerns, federated multi-view clustering solutions have emerged. Existing federated multi-view clustering algorithms often result in misalignment in feature representations among clients, difficulty in integrating information across multiple views, and poor performance in heterogeneous scenarios. To address these challenges, we propose HFMVC, a heterogeneity-aware federated deep multi-view clustering method. Specifically, HFMVC adaptively perceives the degree of heterogeneity in the environment and employs contrastive learning to explore consistency and complementarity information across clients' multi-view data. Besides, we seek consensus among clients where local data originates from the same view, incorporating a contrastive loss between local models and the global model during local training to adjust consistency among local models. Furthermore, we elucidate the sample representation logic for local clustering in different heterogeneous environments, identifying the degree of heterogeneity by computing the within-cluster sum of squares (WCSS) and the average inter-cluster distance (AICD). Extensive experiments verify the superior performance of HFMVC across both IID and Non-IID settings.
AB - Multi-view clustering has proven to be highly effective in exploring consistency information across multiple views/modalities when dealing with large-scale unlabeled data. However, in the real world, multi-view data is often distributed across multiple entities, and due to privacy concerns, federated multi-view clustering solutions have emerged. Existing federated multi-view clustering algorithms often result in misalignment in feature representations among clients, difficulty in integrating information across multiple views, and poor performance in heterogeneous scenarios. To address these challenges, we propose HFMVC, a heterogeneity-aware federated deep multi-view clustering method. Specifically, HFMVC adaptively perceives the degree of heterogeneity in the environment and employs contrastive learning to explore consistency and complementarity information across clients' multi-view data. Besides, we seek consensus among clients where local data originates from the same view, incorporating a contrastive loss between local models and the global model during local training to adjust consistency among local models. Furthermore, we elucidate the sample representation logic for local clustering in different heterogeneous environments, identifying the degree of heterogeneity by computing the within-cluster sum of squares (WCSS) and the average inter-cluster distance (AICD). Extensive experiments verify the superior performance of HFMVC across both IID and Non-IID settings.
KW - contrastive learning
KW - federated learning
KW - multi-view clustering
UR - http://www.scopus.com/inward/record.url?scp=85209806779&partnerID=8YFLogxK
U2 - 10.1145/3664647.3681302
DO - 10.1145/3664647.3681302
M3 - Article in proceedings
AN - SCOPUS:85209806779
T3 - MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia
SP - 9184
EP - 9193
BT - MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia
PB - Association for Computing Machinery, Inc.
T2 - 32nd ACM International Conference on Multimedia, MM 2024
Y2 - 28 October 2024 through 1 November 2024
ER -