Sageflow: Robust Federated Learning against Both Stragglers and Adversaries
While federated learning (FL) allows efficient model training with local data at edge devices, among major issues still to be resolved are: slow devices known as stragglers and malicious attacks launched by adversaries. While the presence of both of these issues raises serious concerns in practical FL systems, no known schemes or combinations of schemes effectively address them at the same time. We propose Sageflow, staleness-aware grouping with entropy-based filtering and loss-weighted averaging, to handle both stragglers and adversaries simultaneously. Model grouping and weighting according to staleness (arrival delay) provides robustness against stragglers, while entropy-based filtering and loss-weighted averaging, working in a highly complementary fashion at each grouping stage, counter a wide range of adversary attacks. A theoretical bound is established to provide key insights into the convergence behavior of Sageflow. Extensive experimental results show that Sageflow outperforms various existing methods aiming to handle stragglers/adversaries.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Sself: Robust Federated Learning against Stragglers and Adversaries
While federated learning allows efficient model training with local data at edge devices, two major issues that need to be resolved are: slow devices known as stragglers and malicious attacks launched by adversaries. Whi…
Data PoisoningFederated LearningStragglers Are Not Disaster: A Hybrid Federated Learning Algorithm with Delayed Gradients
Federated learning (FL) is a new machine learning framework which trains a joint model across a large amount of decentralized computing devices. Existing methods, e.g., Federated Averaging (FedAvg), are able to provide a…
Federated LearningFederated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
We study the problems of differentially private federated online prediction from experts against both stochastic adversaries and oblivious adversaries. We aim to minimize the average regret on $m$ clients working in para…
Nesterov-Accelerated Robust Federated Learning Over Byzantine Adversaries
We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potent…
Federated LearningFedAS: Bridging Inconsistency in Personalized Federated Learning
Personalized Federated Learning (PFL) is primarily designed to provide customized models for each client to better fit the non-iid distributed client data which is a inherent challenge in Federated Learning. However …
Federated LearningPersonalized Federated Learning