Personalized Federated Learning with Attention-based Client Selection
This addresses data distribution challenges in federated learning for personalized model training, but it appears incremental as it builds on existing PFL methods with a novel selection mechanism.
The paper tackles the problem of non-IID data and data scarcity in personalized federated learning by proposing FedACS, an algorithm with an attention-based client selection mechanism, which shows superiority in experiments on CIFAR10 and FMNIST.
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.