Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.15148 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913180985327616 |
|---|---|
| author | Chen, Zihan Li, Jundong Shen, Cong |
| author_facet | Chen, Zihan Li, Jundong Shen, Cong |
| contents | Personalized Federated Learning (PFL) relies on collective data knowledge to build customized models. However, non-IID data between clients poses significant challenges, as collaborating with clients who have diverse data distributions can harm local model performance, especially with limited training data. To address this issue, we propose FedACS, a new PFL algorithm with an Attention-based Client Selection mechanism. FedACS integrates an attention mechanism to enhance collaboration among clients with similar data distributions and mitigate the data scarcity issue. It prioritizes and allocates resources based on data similarity. We further establish the theoretical convergence behavior of FedACS. Experiments on CIFAR10 and FMNIST validate FedACS's superiority, showcasing its potential to advance personalized federated learning. By tackling non-IID data challenges and data scarcity, FedACS offers promising advances in the field of personalized federated learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15148 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Personalized Federated Learning with Attention-based Client Selection Chen, Zihan Li, Jundong Shen, Cong Machine Learning Information Theory Signal Processing Personalized Federated Learning (PFL) relies on collective data knowledge to build customized models. However, non-IID data between clients poses significant challenges, as collaborating with clients who have diverse data distributions can harm local model performance, especially with limited training data. To address this issue, we propose FedACS, a new PFL algorithm with an Attention-based Client Selection mechanism. FedACS integrates an attention mechanism to enhance collaboration among clients with similar data distributions and mitigate the data scarcity issue. It prioritizes and allocates resources based on data similarity. We further establish the theoretical convergence behavior of FedACS. Experiments on CIFAR10 and FMNIST validate FedACS's superiority, showcasing its potential to advance personalized federated learning. By tackling non-IID data challenges and data scarcity, FedACS offers promising advances in the field of personalized federated learning. |
| title | Personalized Federated Learning with Attention-based Client Selection |
| topic | Machine Learning Information Theory Signal Processing |
| url | https://arxiv.org/abs/2312.15148 |