Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.05098 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914871102144512 |
|---|---|
| author | Fan, Boyu Wu, Chenrui Su, Xiang Hui, Pan |
| author_facet | Fan, Boyu Wu, Chenrui Su, Xiang Hui, Pan |
| contents | Despite extensive research into data heterogeneity in federated learning (FL), system heterogeneity remains a significant yet often overlooked challenge. Traditional FL approaches typically assume homogeneous hardware resources across FL clients, implying that clients can train a global model within a comparable time frame. However, in practical FL systems, clients often have heterogeneous resources, which impacts their training capacity. This discrepancy underscores the importance of exploring model-heterogeneous FL, a paradigm allowing clients to train different models based on their resource capabilities. To address this challenge, we introduce FedTSA, a cluster-based two-stage aggregation method tailored for system heterogeneity in FL. FedTSA begins by clustering clients based on their capabilities, then performs a two-stage aggregation: conventional weight averaging for homogeneous models in Stage 1, and deep mutual learning with a diffusion model for aggregating heterogeneous models in Stage 2. Extensive experiments demonstrate that FedTSA not only outperforms the baselines but also explores various factors influencing model performance, validating FedTSA as a promising approach for model-heterogeneous FL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05098 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning Fan, Boyu Wu, Chenrui Su, Xiang Hui, Pan Machine Learning Artificial Intelligence Despite extensive research into data heterogeneity in federated learning (FL), system heterogeneity remains a significant yet often overlooked challenge. Traditional FL approaches typically assume homogeneous hardware resources across FL clients, implying that clients can train a global model within a comparable time frame. However, in practical FL systems, clients often have heterogeneous resources, which impacts their training capacity. This discrepancy underscores the importance of exploring model-heterogeneous FL, a paradigm allowing clients to train different models based on their resource capabilities. To address this challenge, we introduce FedTSA, a cluster-based two-stage aggregation method tailored for system heterogeneity in FL. FedTSA begins by clustering clients based on their capabilities, then performs a two-stage aggregation: conventional weight averaging for homogeneous models in Stage 1, and deep mutual learning with a diffusion model for aggregating heterogeneous models in Stage 2. Extensive experiments demonstrate that FedTSA not only outperforms the baselines but also explores various factors influencing model performance, validating FedTSA as a promising approach for model-heterogeneous FL. |
| title | FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.05098 |