FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909249452376064 |
|---|---|
| author | Islam, Md Sirajul Javaherian, Simin Xu, Fei Yuan, Xu Chen, Li Tzeng, Nian-Feng |
| author_facet | Islam, Md Sirajul Javaherian, Simin Xu, Fei Yuan, Xu Chen, Li Tzeng, Nian-Feng |
| contents | Federated learning (FL) is an emerging distributed machine learning paradigm that enables collaborative training of machine learning models over decentralized devices without exposing their local data. One of the major challenges in FL is the presence of uneven data distributions across client devices, violating the well-known assumption of independent-and-identically-distributed (IID) training samples in conventional machine learning. To address the performance degradation issue incurred by such data heterogeneity, clustered federated learning (CFL) shows its promise by grouping clients into separate learning clusters based on the similarity of their local data distributions. However, state-of-the-art CFL approaches require a large number of communication rounds to learn the distribution similarities during training until the formation of clusters is stabilized. Moreover, some of these algorithms heavily rely on a predefined number of clusters, thus limiting their flexibility and adaptability. In this paper, we propose {\em FedClust}, a novel approach for CFL that leverages the correlation between local model weights and the data distribution of clients. {\em FedClust} groups clients into clusters in a one-shot manner by measuring the similarity degrees among clients based on the strategically selected partial weights of locally trained models. We conduct extensive experiments on four benchmark datasets with different non-IID data settings. Experimental results demonstrate that {\em FedClust} achieves higher model accuracy up to $\sim$45\% as well as faster convergence with a significantly reduced communication cost up to 2.7$\times$ compared to its state-of-the-art counterparts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07124 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering Islam, Md Sirajul Javaherian, Simin Xu, Fei Yuan, Xu Chen, Li Tzeng, Nian-Feng Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning Federated learning (FL) is an emerging distributed machine learning paradigm that enables collaborative training of machine learning models over decentralized devices without exposing their local data. One of the major challenges in FL is the presence of uneven data distributions across client devices, violating the well-known assumption of independent-and-identically-distributed (IID) training samples in conventional machine learning. To address the performance degradation issue incurred by such data heterogeneity, clustered federated learning (CFL) shows its promise by grouping clients into separate learning clusters based on the similarity of their local data distributions. However, state-of-the-art CFL approaches require a large number of communication rounds to learn the distribution similarities during training until the formation of clusters is stabilized. Moreover, some of these algorithms heavily rely on a predefined number of clusters, thus limiting their flexibility and adaptability. In this paper, we propose {\em FedClust}, a novel approach for CFL that leverages the correlation between local model weights and the data distribution of clients. {\em FedClust} groups clients into clusters in a one-shot manner by measuring the similarity degrees among clients based on the strategically selected partial weights of locally trained models. We conduct extensive experiments on four benchmark datasets with different non-IID data settings. Experimental results demonstrate that {\em FedClust} achieves higher model accuracy up to $\sim$45\% as well as faster convergence with a significantly reduced communication cost up to 2.7$\times$ compared to its state-of-the-art counterparts. |
| title | FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2407.07124 |