paper-with-me

Papers

Partial Model Averaging in Federated Learning: Performance Guarantees and Benefits

2022-01-11 · Sunwoo Lee, Anit Kumar Sahu, Chaoyang He, Salman Avestimehr

Local Stochastic Gradient Descent (SGD) with periodic model averaging (FedAvg) is a foundational algorithm in Federated Learning. The algorithm independently runs SGD on multiple workers and periodically averages the model across all the workers. When local SGD runs with many workers, however, the periodic averaging causes a significant model discrepancy across the workers making the global loss converge slowly. While recent advanced optimization methods tackle the issue focused on non-IID settings, there still exists the model discrepancy issue due to the underlying periodic model averaging. We propose a partial model averaging framework that mitigates the model discrepancy issue in Federated Learning. The partial averaging encourages the local models to stay close to each other on parameter space, and it enables to more effectively minimize the global loss. Given a fixed number of iterations and a large number of workers (128), the partial averaging achieves up to 2.2% higher validation accuracy than the periodic full averaging.

📄 PDF Abstract BibTeX arXiv:2201.03789

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Local SGD Local SGD is a distributed training technique that runs SGD independently in parallel on different workers and averages the sequences…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

B^2SFL: A Bi-level Blockchained Architecture for Secure Federated Learning-based Traffic Prediction

2023-10-23 · Hao Guo, Collin Meese, Wanxin Li, Chien-Chung Shen 외

Federated Learning (FL) is a privacy-preserving machine learning (ML) technology that enables collaborative training and learning of a global ML model based on aggregating distributed local model updates. However, securi…

Federated LearningPredictionPrivacy PreservingTraffic Prediction

Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participation

2026-03-21 · Fateme Maleki, Krishnan Raghavan, Farzad Yousefian arxiv

Federated learning (FL) is a communication-efficient collaborative learning framework that enables model training across multiple agents with private local datasets. While the benefits of FL in improving global model per…

Federated Learning

On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks

2023-10-09 · Xin Liu, Wei Li, Dazhi Zhan, Yu Pan 외

Federated learning (FL) is a widely employed distributed paradigm for collaboratively training machine learning models from multiple clients without sharing local data. In practice, FL encounters challenges in dealing wi…

Federated Learning

FedCM: Federated Learning with Client-level Momentum

2021-06-21 · Jing Xu, Sen Wang, LiWei Wang, Andrew Chi-Chih Yao

Federated Learning is a distributed machine learning approach which enables model training without data sharing. In this paper, we propose a new federated learning algorithm, Federated Averaging with Client-level Momentu…

Federated Learning

On Convergence of Federated Averaging Langevin Dynamics

2021-12-09 · Wei Deng, Qian Zhang, Yi-An Ma, Zhao Song 외

We propose a federated averaging Langevin algorithm (FA-LD) for uncertainty quantification and mean predictions with distributed clients. In particular, we generalize beyond normal posterior distributions and consider a …

Uncertainty Quantification