Federated Multi-view Clustering for Remote Sensing Data

Renxiang Guan, Xiang Yang, Hao Yu, Siwei Wang, Suyuan Liu, Wenjing Yang, Jun-Jie Huang, Ao Li, Xinwang Liu, Yuhua Tang
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:37620-37630, 2026.

Abstract

The rapid expansion of remote sensing technology has generated massive amounts of unlabeled multi-view data distributed across different institutions. Analyzing this data presents significant challenges, as centralized processing incurs prohibitive communication costs and raises data privacy concerns. To address these issues, this paper proposes a novel deep federated multi-view clustering (MVC) framework tailored for remote sensing data. Unlike existing methods that transmit sensitive data features, our approach shares only privatized prototypes masked with adaptive noise, ensuring both communication efficiency and privacy preservation. First, we employ superpixel segmentation to reduce the spatial dimensionality of remote sensing data, lowering computational burdens. Furthermore, to resolve the inconsistency of cluster assignments across different clients, we design a co-occurrence structural alignment module that synchronizes local models. Finally, we incorporate a wasserstein prototype contrastive learning mechanism, which models clusters as distributions rather than points, to enhance global consistency and robustness against data heterogeneity. Extensive experiments on four public datasets demonstrate that our framework achieves superior clustering performance and efficiency compared to state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-guan26j, title = {Federated Multi-view Clustering for Remote Sensing Data}, author = {Guan, Renxiang and Yang, Xiang and Yu, Hao and Wang, Siwei and Liu, Suyuan and Yang, Wenjing and Huang, Jun-Jie and Li, Ao and Liu, Xinwang and Tang, Yuhua}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {37620--37630}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/guan26j/guan26j.pdf}, url = {https://proceedings.mlr.press/v306/guan26j.html}, abstract = {The rapid expansion of remote sensing technology has generated massive amounts of unlabeled multi-view data distributed across different institutions. Analyzing this data presents significant challenges, as centralized processing incurs prohibitive communication costs and raises data privacy concerns. To address these issues, this paper proposes a novel deep federated multi-view clustering (MVC) framework tailored for remote sensing data. Unlike existing methods that transmit sensitive data features, our approach shares only privatized prototypes masked with adaptive noise, ensuring both communication efficiency and privacy preservation. First, we employ superpixel segmentation to reduce the spatial dimensionality of remote sensing data, lowering computational burdens. Furthermore, to resolve the inconsistency of cluster assignments across different clients, we design a co-occurrence structural alignment module that synchronizes local models. Finally, we incorporate a wasserstein prototype contrastive learning mechanism, which models clusters as distributions rather than points, to enhance global consistency and robustness against data heterogeneity. Extensive experiments on four public datasets demonstrate that our framework achieves superior clustering performance and efficiency compared to state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Federated Multi-view Clustering for Remote Sensing Data %A Renxiang Guan %A Xiang Yang %A Hao Yu %A Siwei Wang %A Suyuan Liu %A Wenjing Yang %A Jun-Jie Huang %A Ao Li %A Xinwang Liu %A Yuhua Tang %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-guan26j %I PMLR %P 37620--37630 %U https://proceedings.mlr.press/v306/guan26j.html %V 306 %X The rapid expansion of remote sensing technology has generated massive amounts of unlabeled multi-view data distributed across different institutions. Analyzing this data presents significant challenges, as centralized processing incurs prohibitive communication costs and raises data privacy concerns. To address these issues, this paper proposes a novel deep federated multi-view clustering (MVC) framework tailored for remote sensing data. Unlike existing methods that transmit sensitive data features, our approach shares only privatized prototypes masked with adaptive noise, ensuring both communication efficiency and privacy preservation. First, we employ superpixel segmentation to reduce the spatial dimensionality of remote sensing data, lowering computational burdens. Furthermore, to resolve the inconsistency of cluster assignments across different clients, we design a co-occurrence structural alignment module that synchronizes local models. Finally, we incorporate a wasserstein prototype contrastive learning mechanism, which models clusters as distributions rather than points, to enhance global consistency and robustness against data heterogeneity. Extensive experiments on four public datasets demonstrate that our framework achieves superior clustering performance and efficiency compared to state-of-the-art methods.
APA
Guan, R., Yang, X., Yu, H., Wang, S., Liu, S., Yang, W., Huang, J., Li, A., Liu, X. & Tang, Y.. (2026). Federated Multi-view Clustering for Remote Sensing Data. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:37620-37630 Available from https://proceedings.mlr.press/v306/guan26j.html.

Related Material