paper-with-me

홈 › Papers

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

2021-06-08 · NeurIPS 2021 12 · Xinran Gu, Kaixuan Huang, Jingzhao Zhang, Longbo Huang

Federated Learning (FL) coordinates with numerous heterogeneous devices to collaboratively train a shared model while preserving user privacy. Despite its multiple advantages, FL faces new challenges. One challenge arises when devices drop out of the training process beyond the control of the central server. In this case, the convergence of popular FL algorithms such as FedAvg is severely influenced by the straggling devices. To tackle this challenge, we study federated learning algorithms under arbitrary device unavailability and propose an algorithm named Memory-augmented Impatient Federated Averaging (MIFA). Our algorithm efficiently avoids excessive latency induced by inactive devices, and corrects the gradient bias using the memorized latest updates from the devices. We prove that MIFA achieves minimax optimal convergence rates on non-i.i.d. data for both strongly convex and non-convex smooth functions. We also provide an explicit characterization of the improvement over baseline algorithms through a case study, and validate the results by numerical experiments on real-world datasets.

📄 PDF Abstract BibTeX arXiv:2106.04159

Code (1)

hmgxr128/mifa_code pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Federated Learning in the Presence of Adversarial Client Unavailability

2023-05-31 · Lili Su, Ming Xiang, Jiaming Xu, Pengkun Yang

Federated learning is a decentralized machine learning framework that enables collaborative model training without revealing raw data. Due to the diverse hardware and software limitations, a client may not always be avai…

Federated LearningSelection bias

Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability

2024-09-26 · Ming Xiang, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong 외

Addressing intermittent client availability is critical for the real-world deployment of federated learning algorithms. Most prior work either overlooks the potential non-stationarity in the dynamics of client unavailabi…

Federated Learning

FedCluster: Boosting the Convergence of Federated Learning via Cluster-Cycling

2020-09-22 · Cheng Chen, Ziyi Chen, Yi Zhou, Bhavya Kailkhura

We develop FedCluster--a novel federated learning framework with improved optimization efficiency, and investigate its theoretical convergence properties. The FedCluster groups the devices into multiple clusters that per…

Federated Learning

Federated Learning with Erroneous Communication Links

2022-01-31 · Mahyar Shirvanimoghaddam, Ayoob Salari, Yifeng Gao, Aradhika Guha

In this paper, we consider the federated learning (FL) problem in the presence of communication errors. We model the link between the devices and the central node (CN) by a packet erasure channel, where the local paramet…

Federated Learning

CorrFL: Correlation-based Neural Network Architecture for Unavailability Concerns in a Heterogeneous IoT Environment

2023-05-23 · IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2023 5 · Shaer, Ibrahim; Shami, Abdallah

The Federated Learning (FL) paradigm faces several challenges that limit its application in real-world environments. These challenges include the local models’ architecture heterogeneity and the unavailability of distrib…

Federated LearningRepresentation Learning