Interaction-Aware Gaussian Weighting for Clustered Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910925644103680 |
|---|---|
| author | Licciardi, Alessandro Leo, Davide Fanì, Eros Caputo, Barbara Ciccone, Marco |
| author_facet | Licciardi, Alessandro Leo, Davide Fanì, Eros Caputo, Barbara Ciccone, Marco |
| contents | 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 clustered FL method, 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03340 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interaction-Aware Gaussian Weighting for Clustered Federated Learning Licciardi, Alessandro Leo, Davide Fanì, Eros Caputo, Barbara Ciccone, Marco Machine Learning 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 clustered FL method, 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. |
| title | Interaction-Aware Gaussian Weighting for Clustered Federated Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.03340 |