Federated Deep Multi-View Clustering with Global Self-Supervision
- URL: http://arxiv.org/abs/2309.13697v1
- Date: Sun, 24 Sep 2023 17:07:01 GMT
- Title: Federated Deep Multi-View Clustering with Global Self-Supervision
- Authors: Xinyue Chen, Jie Xu, Yazhou Ren, Xiaorong Pu, Ce Zhu, Xiaofeng Zhu,
Zhifeng Hao, Lifang He
- Abstract summary: Federated multi-view clustering has the potential to learn a global clustering model from data distributed across multiple devices.
In this setting, label information is unknown and data privacy must be preserved.
We propose a novel federated deep multi-view clustering method that can mine complementary cluster structures from multiple clients.
- Score: 51.639891178519136
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Federated multi-view clustering has the potential to learn a global
clustering model from data distributed across multiple devices. In this
setting, label information is unknown and data privacy must be preserved,
leading to two major challenges. First, views on different clients often have
feature heterogeneity, and mining their complementary cluster information is
not trivial. Second, the storage and usage of data from multiple clients in a
distributed environment can lead to incompleteness of multi-view data. To
address these challenges, we propose a novel federated deep multi-view
clustering method that can mine complementary cluster structures from multiple
clients, while dealing with data incompleteness and privacy concerns.
Specifically, in the server environment, we propose sample alignment and data
extension techniques to explore the complementary cluster structures of
multiple views. The server then distributes global prototypes and global
pseudo-labels to each client as global self-supervised information. In the
client environment, multiple clients use the global self-supervised information
and deep autoencoders to learn view-specific cluster assignments and embedded
features, which are then uploaded to the server for refining the global
self-supervised information. Finally, the results of our extensive experiments
demonstrate that our proposed method exhibits superior performance in
addressing the challenges of incomplete multi-view data in distributed
environments.
Related papers
- Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views [16.440354614784507]
Federated multi-view clustering (FedMVC) has emerged to explore cluster structures in multi-view data distributed on multiple clients.
We propose a novel FedMVC framework, which concurrently addresses two challenges associated with heterogeneous hybrid views.
Our method can handle the heterogeneous hybrid views in FedMVC and outperforms state-of-the-art methods.
arXiv Detail & Related papers (2024-10-12T10:43:47Z) - Federated Incomplete Multi-View Clustering with Heterogeneous Graph Neural Networks [21.710283538891968]
Federated multi-view clustering offers the potential to develop a global clustering model using data distributed across multiple devices.
Current methods face challenges due to the absence of label information and the paramount importance of data privacy.
We introduce a federated incomplete multi-view clustering framework with heterogeneous graph neural networks (FIM-GNNs)
arXiv Detail & Related papers (2024-06-12T07:16:00Z) - FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity [43.71967577443732]
Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server.
Recent research is limited to simply using averaged signals as a form of regularization and only focusing on one aspect of these non-IID challenges.
We propose a dual-clustered feature contrast-based FL framework with dual focuses.
arXiv Detail & Related papers (2024-04-14T13:56:30Z) - CDIMC-net: Cognitive Deep Incomplete Multi-view Clustering Network [53.72046586512026]
We propose a novel incomplete multi-view clustering network, called Cognitive Deep Incomplete Multi-view Clustering Network (CDIMC-net)
It captures the high-level features and local structure of each view by incorporating the view-specific deep encoders and graph embedding strategy into a framework.
Based on the human cognition, i.e., learning from easy to hard, it introduces a self-paced strategy to select the most confident samples for model training.
arXiv Detail & Related papers (2024-03-28T15:45:03Z) - Deep Clustering: A Comprehensive Survey [53.387957674512585]
Clustering analysis plays an indispensable role in machine learning and data mining.
Deep clustering, which can learn clustering-friendly representations using deep neural networks, has been broadly applied in a wide range of clustering tasks.
Existing surveys for deep clustering mainly focus on the single-view fields and the network architectures, ignoring the complex application scenarios of clustering.
arXiv Detail & Related papers (2022-10-09T02:31:32Z) - Federated Multi-Target Domain Adaptation [99.93375364579484]
Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy.
We consider a more practical scenario where the distributed client data is unlabeled, and a centralized labeled dataset is available on the server.
We propose an effective DualAdapt method to address the new challenges.
arXiv Detail & Related papers (2021-08-17T17:53:05Z) - Error-Robust Multi-View Clustering: Progress, Challenges and
Opportunities [67.54503077766171]
Since label information is often expensive to acquire, multi-view clustering has gained growing interest.
Error-robust multi-view clustering approaches with explicit error removal formulation can be structured into five broad research categories.
This survey summarizes and reviews recent advances in error-robust clustering for multi-view data.
arXiv Detail & Related papers (2021-05-07T04:03:02Z) - Multi-view Subspace Clustering Networks with Local and Global Graph
Information [19.64977233324484]
The goal of this study is to explore the underlying grouping structure of data collected from different fields or measurements.
We propose the novel multi-view subspace clustering networks with local and global graph information, termed MSCNLG.
As an end-to-end trainable framework, the proposed method fully investigates the valuable information of multiple views.
arXiv Detail & Related papers (2020-10-19T09:00:19Z) - Deep Incomplete Multi-View Multiple Clusterings [41.43164409639238]
We introduce a deep incomplete multi-view multiple clusterings framework, which achieves the completion of data view and multiple shared representations simultaneously.
Experiments on benchmark datasets confirm that DiMVMC outperforms the state-of-the-art competitors in generating multiple clusterings with high diversity and quality.
arXiv Detail & Related papers (2020-10-02T08:01:24Z) - Generative Partial Multi-View Clustering [133.36721417531734]
We propose a generative partial multi-view clustering model, named as GP-MVC, to address the incomplete multi-view problem.
First, multi-view encoder networks are trained to learn common low-dimensional representations, followed by a clustering layer to capture the consistent cluster structure across multiple views.
Second, view-specific generative adversarial networks are developed to generate the missing data of one view conditioning on the shared representation given by other views.
arXiv Detail & Related papers (2020-03-29T17:48:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.