Communication-Efficient and Drift-Robust Federated Learning via Elastic Net

2022-10-06 · Seonhyeong Kim, Jiheon Woo, Daewon Seo, Yongjune Kim

Federated learning (FL) is a distributed method to train a global model over a set of local clients while keeping data localized. It reduces the risks of privacy and security but faces important challenges including expensive communication costs and client drift issues. To address these issues, we propose FedElasticNet, a communication-efficient and drift-robust FL framework leveraging the elastic net. It repurposes two types of the elastic net regularizers (i.e., $\ell_1$ and $\ell_2$ penalties on the local model updates): (1) the $\ell_1$-norm regularizer sparsifies the local updates to reduce the communication costs and (2) the $\ell_2$-norm regularizer resolves the client drift problem by limiting the impact of drifting local updates due to data heterogeneity. FedElasticNet is a general framework for FL; hence, without additional costs, it can be integrated into prior FL techniques, e.g., FedAvg, FedProx, SCAFFOLD, and FedDyn. We show that our framework effectively resolves the communication cost and client drift problems simultaneously.

📄 PDF Abstract BibTeX arXiv:2210.02940

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Elastic Aggregation for Federated Optimization

2023-01-01 · CVPR 2023 1 · Dengsheng Chen, Jie Hu, Vince Junkai Tan, Xiaoming Wei 외

Federated learning enables the privacy-preserving training of neural network models using real-world data across distributed clients. FedAvg has become the preferred optimizer for federated learning because of its si…

Federated Learning Privacy Preserving

Federated Optimization with Doubly Regularized Drift Correction

2024-04-12 · Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich

Federated learning is a distributed optimization paradigm that allows training machine learning models across decentralized devices while keeping the data localized. The standard method, FedAvg, suffers from client drift…

Distributed Optimization Federated Learning

Adversarial training in communication constrained federated learning

2021-03-01 · Devansh Shah, Parijat Dube, Supriyo Chakraborty, Ashish Verma

Federated learning enables model training over a distributed corpus of agent data. However, the trained model is vulnerable to adversarial examples, designed to elicit misclassification. We study the feasibility of using…

Attribute Federated Learning

REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecasting

2024-11-21 · Qingxiang Liu, Sheng Sun, Yuxuan Liang, Xiaolong Xu 외

Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However,…