Clustered Federated Learning via Embedding Distributions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916785374101504 |
|---|---|
| author | Zhang, Dekai Williams, Matthew Toni, Francesca |
| author_facet | Zhang, Dekai Williams, Matthew Toni, Francesca |
| contents | Federated learning (FL) is a widely used framework for machine learning in distributed data environments where clients hold data that cannot be easily centralised, such as for data protection reasons. FL, however, is known to be vulnerable to non-IID data. Clustered FL addresses this issue by finding more homogeneous clusters of clients. We propose a novel one-shot clustering method, EMD-CFL, using the Earth Mover's distance (EMD) between data distributions in embedding space. We theoretically motivate the use of EMDs using results from the domain adaptation literature and demonstrate empirically superior clustering performance in extensive comparisons against 16 baselines and on a range of challenging datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_07769 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Clustered Federated Learning via Embedding Distributions Zhang, Dekai Williams, Matthew Toni, Francesca Machine Learning Federated learning (FL) is a widely used framework for machine learning in distributed data environments where clients hold data that cannot be easily centralised, such as for data protection reasons. FL, however, is known to be vulnerable to non-IID data. Clustered FL addresses this issue by finding more homogeneous clusters of clients. We propose a novel one-shot clustering method, EMD-CFL, using the Earth Mover's distance (EMD) between data distributions in embedding space. We theoretically motivate the use of EMDs using results from the domain adaptation literature and demonstrate empirically superior clustering performance in extensive comparisons against 16 baselines and on a range of challenging datasets. |
| title | Clustered Federated Learning via Embedding Distributions |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.07769 |