Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing
Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm. Nonetheless, the substantial distribution shifts among clients pose a considerable challenge to the performance of current FL algorithms. To mitigate this challenge, various methods have been proposed to enhance the FL training process. This paper endeavors to tackle the issue of data heterogeneity from another perspective -- by improving FL algorithms prior to the actual training stage. Specifically, we introduce the Client2Vec mechanism, which generates a unique client index for each client before the commencement of FL training. Subsequently, we leverage the generated client index to enhance the subsequent FL training process. To demonstrate the effectiveness of the proposed Client2Vec method, we conduct three case studies that assess the impact of the client index on the FL training process. These case studies encompass enhanced client sampling, model aggregation, and local training. Extensive experiments conducted on diverse datasets and model architectures show the efficacy of Client2Vec across all three case studies. Our code is avaliable at \url{https://github.com/LINs-lab/client2vec}.
Code (1)
Tasks
Federated LearningPrivacy PreservingSimilar Papers 제목 키워드 기반
pFedBBN: A Personalized Federated Test-Time Adaptation with Balanced Batch Normalization for Class-Imbalanced Data
Test-time adaptation (TTA) in federated learning (FL) is crucial for handling unseen data distributions across clients, particularly when faced with domain shifts and skewed class distributions. Class Imbalance (CI) rema…
Test-time AdaptationFederated LearningVirtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learning
Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such…
Graph LearningGraph Property PredictionProperty PredictionFed-ADE: Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift
Federated learning (FL) in post-deployment settings must adapt to non-stationary data streams across heterogeneous clients without access to ground-truth labels. A major challenge is learning rate selection under client-…
Federated LearningDetecting Atypical Clients in Federated Learning via Representation-Level Divergence
Federated learning enables collaborative training across distributed clients with heterogeneous data, but such heterogeneity often leads to unstable updates and degraded global performance. Moreover, in practical deploym…
Federated LearningFLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy. Traditional FL methods often use a global model to fit all clients, assuming that clients' data are inde…
Test-time AdaptationFederated Learning