Interaction-Aware Gaussian Weighting for Clustered Federated Learning

Alessandro Licciardi, Davide Leo, Eros Fanı̀, Barbara Caputo, Marco Ciccone
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:37642-37666, 2025.

Abstract

Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustering method for FL, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more robust and personalized model on the identified clusters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-licciardi25a, title = {Interaction-Aware {G}aussian Weighting for Clustered Federated Learning}, author = {Licciardi, Alessandro and Leo, Davide and Fan\`{\i}, Eros and Caputo, Barbara and Ciccone, Marco}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {37642--37666}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/licciardi25a/licciardi25a.pdf}, url = {https://proceedings.mlr.press/v267/licciardi25a.html}, abstract = {Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustering method for FL, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more robust and personalized model on the identified clusters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach.} }
Endnote
%0 Conference Paper %T Interaction-Aware Gaussian Weighting for Clustered Federated Learning %A Alessandro Licciardi %A Davide Leo %A Eros Fanı̀ %A Barbara Caputo %A Marco Ciccone %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-licciardi25a %I PMLR %P 37642--37666 %U https://proceedings.mlr.press/v267/licciardi25a.html %V 267 %X Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustering method for FL, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more robust and personalized model on the identified clusters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach.
APA
Licciardi, A., Leo, D., Fanı̀, E., Caputo, B. & Ciccone, M.. (2025). Interaction-Aware Gaussian Weighting for Clustered Federated Learning. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:37642-37666 Available from https://proceedings.mlr.press/v267/licciardi25a.html.

Related Material