mlsanityData to 7 Oct 2026

Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views

arXiv 2410.09484 ↗First posted 12 Oct 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, federated multi-view clustering (FedMVC) has emerged to explore cluster structures in multi-view data distributed on multiple clients. Existing approaches often assume that clients are isomorphic and all of them belong to either single-view clients or multi-view clients. Despite their success, these methods also present limitations when dealing with practical FedMVC scenarios involving heterogeneous hybrid views, where a mixture of both single-view and multi-view clients exhibit varying degrees of heterogeneity. In this paper, we propose a novel FedMVC framework, which concurrently addresses two challenges associated with heterogeneous hybrid views, i.e., client gap and view gap. To address the client gap, we design a local-synergistic contrastive learning approach that helps single-view clients and multi-view clients achieve consistency for mitigating heterogeneity among all clients. To address the view gap, we develop a global-specific weighting aggregation method, which encourages global models to learn complementary features from hybrid views. The interplay between local-synergistic contrastive learning and global-specific weighting aggregation mutually enhances the exploration of the data cluster structures distributed on multiple clients. Theoretical analysis and extensive experiments demonstrate that our method can handle the heterogeneous hybrid views in FedMVC and outperforms state-of-the-art methods. The code is available at urlhttps://github.com/5Martina5/FMCSC.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 59 references that are in the map. First posted on arXiv 12 Oct 2024.

Builds on

23 of 59 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  6. 2020Federated Unsupervised Representation Learningcited by 92
  7. 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 85
  8. 2021Multi-level Feature Learning for Contrastive Multi-view Clusteringcited by 73
  9. 2023Factorized Contrastive Learning: Going Beyond Multi-view Redundancycited by 73
  10. 2021Self-Supervised Discriminative Feature Learning for Deep Multi-View Clusteringcited by 41
  11. 2023Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignmentcited by 33
  12. 2023GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clusteringcited by 30
11 more
  1. 2020Deep Robust Clustering by Contrastive Learningcited by 25
  2. 2023Incomplete Multi-view Clustering via Prototype-based Imputationcited by 21
  3. 2023Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarioscited by 19
  4. 2022Localized Sparse Incomplete Multi-view Clusteringcited by 17
  5. 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspectivecited by 14
  6. 2020A Federated Multi-View Deep Learning Framework for Privacy-Preserving Recommendationscited by 13
  7. 2023Deep Multi-View Subspace Clustering with Anchor Graphcited by 13
  8. 2021Federated Multi-View Learning for Private Medical Data Integration and Analysiscited by 12
  9. 2021Non-Linear Fusion for Self-Paced Multi-View Clusteringcited by 9
  10. 2023Federated Deep Multi-View Clustering with Global Self-Supervisioncited by 5
  11. 2023Joint Projection Learning and Tensor Decomposition Based Incomplete Multi-view Clusteringcited by 5

Built on by

Not cited yet.