On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond
- URL: http://arxiv.org/abs/2310.02702v4
- Date: Fri, 13 Dec 2024 16:34:56 GMT
- Title: On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond
- Authors: Dun Zeng, Zenglin Xu, Shiyu Liu, Yu Pan, Qifan Wang, Xiaoying Tang,
- Abstract summary: Federated averaging (FedAvg) is the most fundamental algorithm in Federated learning (FL)
Recent empirical results show that FedAvg can perform well in many real-world heterogeneous tasks.
We present a simple and effective FedAvg variant termed FedAWARE.
- Score: 37.894835756324454
- License:
- Abstract: Federated averaging (FedAvg) is the most fundamental algorithm in Federated learning (FL). Previous theoretical results assert that FedAvg convergence and generalization degenerate under heterogeneous clients. However, recent empirical results show that FedAvg can perform well in many real-world heterogeneous tasks. These results reveal an inconsistency between FL theory and practice that is not fully explained. In this paper, we show that common heterogeneity measures contribute to this inconsistency based on rigorous convergence analysis. Furthermore, we introduce a new measure \textit{client consensus dynamics} and prove that \textit{FedAvg can effectively handle client heterogeneity when an appropriate aggregation strategy is used}. Building on this theoretical insight, we present a simple and effective FedAvg variant termed FedAWARE. Extensive experiments on three datasets and two modern neural network architectures demonstrate that FedAWARE ensures faster convergence and better generalization in heterogeneous client settings. Moreover, our results show that FedAWARE can significantly enhance the generalization performance of advanced FL algorithms when used as a plug-in module.
Related papers
- Federated Generalised Variational Inference: A Robust Probabilistic Federated Learning Framework [12.454538785810259]
FedGVI is a probabilistic Federated Learning (FL) framework that is provably robust to both prior and likelihood misspecification.
We offer theoretical analysis in terms of fixed-point convergence, optimality of the cavity distribution, and provable robustness.
arXiv Detail & Related papers (2025-02-02T16:39:37Z) - Factor-Assisted Federated Learning for Personalized Optimization with
Heterogeneous Data [6.024145412139383]
Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy.
Data in different clients contain both common knowledge and personalized knowledge.
We develop a novel personalized federated learning framework for heterogeneous data, which we refer to as FedSplit.
arXiv Detail & Related papers (2023-12-07T13:05:47Z) - Momentum Benefits Non-IID Federated Learning Simply and Provably [22.800862422479913]
Federated learning is a powerful paradigm for large-scale machine learning.
FedAvg and SCAFFOLD are two prominent algorithms to address these challenges.
This paper explores the utilization of momentum to enhance the performance of FedAvg and SCAFFOLD.
arXiv Detail & Related papers (2023-06-28T18:52:27Z) - Federated Conformal Predictors for Distributed Uncertainty
Quantification [83.50609351513886]
Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning.
In this paper, we extend conformal prediction to the federated learning setting.
We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction framework.
arXiv Detail & Related papers (2023-05-27T19:57:27Z) - Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated
Learning Framework [82.36466358313025]
We propose a primal-dual FL algorithm, termed FedVRA, that allows one to adaptively control the variance-reduction level and biasness of the global model.
Experiments based on (semi-supervised) image classification tasks demonstrate superiority of FedVRA over the existing schemes.
arXiv Detail & Related papers (2022-12-03T03:27:51Z) - On the Unreasonable Effectiveness of Federated Averaging with
Heterogeneous Data [39.600069116159695]
Existing theory predicts that data heterogeneity will degrade the performance of the Federated Averaging (FedAvg) algorithm in federated learning.
This paper explains the seemingly unreasonable effectiveness of FedAvg that contradicts the previous theoretical predictions.
arXiv Detail & Related papers (2022-06-09T18:25:25Z) - FedAvg with Fine Tuning: Local Updates Lead to Representation Learning [54.65133770989836]
Federated Averaging (FedAvg) algorithm consists of alternating between a few local gradient updates at client nodes, followed by a model averaging update at the server.
We show that the reason behind generalizability of the FedAvg's output is its power in learning the common data representation among the clients' tasks.
We also provide empirical evidence demonstrating FedAvg's representation learning ability in federated image classification with heterogeneous data.
arXiv Detail & Related papers (2022-05-27T00:55:24Z) - Federated Composite Optimization [28.11253930828807]
Federated Learning (FL) is a distributed learning paradigm that scales on-device learning collaboratively and privately.
Standard FL algorithms such as FedAvg are primarily geared towards smooth unconstrained settings.
We propose a new primal-dual algorithm, Federated Dual Averaging (FedDualAvg), which by employing a novel server dual averaging procedure circumvents the curse of primal averaging.
arXiv Detail & Related papers (2020-11-17T06:54:06Z) - A Unified Linear Speedup Analysis of Federated Averaging and Nesterov
FedAvg [49.76940694847521]
Federated learning (FL) learns a model jointly from a set of participating devices without sharing each other's privately held data.
In this paper, we focus on Federated Averaging (FedAvg), one of the most popular and effective FL algorithms in use today.
We show that FedAvg enjoys linear speedup in each case, although with different convergence rates and communication efficiencies.
arXiv Detail & Related papers (2020-07-11T05:59:08Z) - FedDANE: A Federated Newton-Type Method [49.9423212899788]
Federated learning aims to jointly learn low statistical models over massively distributed datasets.
We propose FedDANE, an optimization that we adapt from DANE, to handle federated learning.
arXiv Detail & Related papers (2020-01-07T07:44:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.