FedAWARE: Maximizing Gradient Diversity for Heterogeneous Federated Server-side Optimization
- URL: http://arxiv.org/abs/2310.02702v3
- Date: Fri, 24 May 2024 16:13:22 GMT
- Title: FedAWARE: Maximizing Gradient Diversity for Heterogeneous Federated Server-side Optimization
- Authors: Dun Zeng, Zenglin Xu, Yu Pan, Qifan Wang, Xiaoying Tang,
- Abstract summary: textscFedAWARE can enhance the performance of FL algorithms as a plug-in module.
textscFedAWARE can enhance the performance of FL algorithms as a plug-in module.
- Score: 37.743911787044475
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Federated learning (FL) is a distributed learning framework where numerous clients collaborate with a central server to train a model without sharing local data. However, the standard federated optimization in real-world applications faces both statistical and system heterogeneity challenges, which result in unfavorable convergence behavior. The previous works attempted to modify the local training process (client-side) to tackle heterogeneity challenges. However, they ignored that the updates on the server side can coordinate the diverse local updates efficiently. This work explores the effect of server-side updates against heterogeneity issues. We first introduce the gradient diversity maximization direction findings, suggesting the global model moves continuously in this direction for fast and stable convergence. Then, we derive a novel server-side optimizer \textsc{FedAWARE} with rigorous convergence analysis for general non-convex settings. Our extensive experiments across multiple heterogeneous federated settings using four datasets showcase that \textsc{FedAWARE} achieves competitive convergence performance in comparison to state-of-the-art adaptive federated optimizers. Furthermore, our results show that \textsc{FedAWARE} can enhance the performance of FL algorithms as a plug-in module. Our source code is available at \url{https://github.com/dunzeng/FedAWARE}.
Related papers
- FLASH: Federated Learning Across Simultaneous Heterogeneities [54.80435317208111]
FLASH(Federated Learning Across Simultaneous Heterogeneities) is a lightweight and flexible client selection algorithm.
It outperforms state-of-the-art FL frameworks under extensive sources of Heterogeneities.
It achieves substantial and consistent improvements over state-of-the-art baselines.
arXiv Detail & Related papers (2024-02-13T20:04:39Z) - Rethinking Client Drift in Federated Learning: A Logit Perspective [125.35844582366441]
Federated Learning (FL) enables multiple clients to collaboratively learn in a distributed way, allowing for privacy protection.
We find that the difference in logits between the local and global models increases as the model is continuously updated.
We propose a new algorithm, named FedCSD, a Class prototype Similarity Distillation in a federated framework to align the local and global models.
arXiv Detail & Related papers (2023-08-20T04:41:01Z) - Towards Instance-adaptive Inference for Federated Learning [80.38701896056828]
Federated learning (FL) is a distributed learning paradigm that enables multiple clients to learn a powerful global model by aggregating local training.
In this paper, we present a novel FL algorithm, i.e., FedIns, to handle intra-client data heterogeneity by enabling instance-adaptive inference in the FL framework.
Our experiments show that our FedIns outperforms state-of-the-art FL algorithms, e.g., a 6.64% improvement against the top-performing method with less than 15% communication cost on Tiny-ImageNet.
arXiv Detail & Related papers (2023-08-11T09:58:47Z) - Locally Adaptive Federated Learning [30.19411641685853]
Federated learning is a paradigm of distributed machine learning in which multiple clients coordinate with a central server to learn a model.
Standard federated optimization methods such as Federated Averaging (FedAvg) ensure generalization among the clients.
We propose locally federated learning algorithms, that leverage the local geometric information for each client function.
arXiv Detail & Related papers (2023-07-12T17:02:32Z) - Neural Collapse Inspired Federated Learning with Non-iid Data [31.576588815816095]
Non-independent and identically distributed (non-iid) characteristics cause significant differences in local updates and affect the performance of the central server.
Inspired by the phenomenon of neural collapse, we force each client to be optimized toward an optimal global structure for classification.
Our method can improve the performance with faster convergence speed on different-size datasets.
arXiv Detail & Related papers (2023-03-27T05:29:53Z) - FedSkip: Combatting Statistical Heterogeneity with Federated Skip
Aggregation [95.85026305874824]
We introduce a data-driven approach called FedSkip to improve the client optima by periodically skipping federated averaging and scattering local models to the cross devices.
We conduct extensive experiments on a range of datasets to demonstrate that FedSkip achieves much higher accuracy, better aggregation efficiency and competing communication efficiency.
arXiv Detail & Related papers (2022-12-14T13:57:01Z) - Speeding up Heterogeneous Federated Learning with Sequentially Trained
Superclients [19.496278017418113]
Federated Learning (FL) allows training machine learning models in privacy-constrained scenarios by enabling the cooperation of edge devices without requiring local data sharing.
This approach raises several challenges due to the different statistical distribution of the local datasets and the clients' computational heterogeneity.
We propose FedSeq, a novel framework leveraging the sequential training of subgroups of heterogeneous clients, i.e. superclients, to emulate the centralized paradigm in a privacy-compliant way.
arXiv Detail & Related papers (2022-01-26T12:33:23Z) - Local Adaptivity in Federated Learning: Convergence and Consistency [25.293584783673413]
Federated learning (FL) framework trains a machine learning model using decentralized data stored at edge client devices by periodically aggregating locally trained models.
We show in both theory and practice that while local adaptive methods can accelerate convergence, they can cause a non-vanishing solution bias.
We propose correction techniques to overcome this inconsistency and complement the local adaptive methods for FL.
arXiv Detail & Related papers (2021-06-04T07:36:59Z) - Faster Non-Convex Federated Learning via Global and Local Momentum [57.52663209739171]
textttFedGLOMO is the first (first-order) FLtexttFedGLOMO algorithm.
Our algorithm is provably optimal even with communication between the clients and the server.
arXiv Detail & Related papers (2020-12-07T21:05:31Z) - Adaptive Federated Optimization [43.78438670284309]
In Federated learning, a large number of clients coordinate with a central server to learn a model without sharing their own data.
adaptive optimization methods have notable success in combating such issues.
We show that the use adaptives can significantly improve the performance of federated learning.
arXiv Detail & Related papers (2020-02-29T16:37:29Z)
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.