Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
University of Pennsylvania（宾夕法尼亚大学）
Aritra Mitra, Rayana Jaafar, George J. Pappas, Hamed Hassani
备注：
Compared to the previous version, this version contains an additional result pertaining to a general stochastic oracle model. It also includes additional comparisons of our algorithm and results with relevant existing works
We consider a standard federated learning (FL) architecture where a group of clients periodically coordinate with a central server to train a statistical model. We develop a general algorithmic framework called FedLin to tackle some of the key challenges intrinsic to FL, namely objective heterogeneity, systems heterogeneity, and infrequent and imprecise communication. Our framework is motivated by the observation that under these challenges, various existing FL algorithms suffer from a fundamental speed-accuracy conflict: they either guarantee linear convergence but to an incorrect point, or convergence to the global minimum but at a sub-linear rate, i.e., fast convergence comes at the expense of accuracy. In contrast, when the clients' local loss functions are smooth and strongly convex, we show that FedLin guarantees linear convergence to the global minimum, despite arbitrary objective and systems heterogeneity. We then establish matching upper and lower bounds on the convergence rate of FedLin that highlight the effects of intermittent communication. Finally, we show that FedLin preserves linear convergence rates under aggressive gradient sparsification, and quantify the effect of the compression level on the convergence rate. Our work is the first to provide tight linear convergence rate guarantees, and constitutes the first comprehensive analysis of gradient sparsification in FL.
Data-heterogeneous federated learning (FL) systems suffer from two significant sources of convergence error: 1) client drift error caused by performing multiple local optimization steps at clients, and 2) partial client participation error caused by the fact that only a small subset of the edge clients participate in every training round. We find that among these, only the former has received significant attention in the literature. To remedy this, we propose FedVARP, a novel variance reduction algorithm applied at the server that eliminates error due to partial client participation. To do so,…
Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on clients' devices without any guarantees for either homogeneity or stationarity of the local private data. The need for continual training has also risen, due to the ever-increasing production of in-task data. However, pursuing both directions at the same time is challenging, since client data privacy is a major constraint, especially for rehearsal methods. Herein, we propose a novel algorithm to address the incremental lea…
Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Yale University（耶鲁大学）
Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from slow wall-clock time for convergence due to high degrees of system heterogeneity and statistical heterogeneity. This paper aims to design an adaptive client sampling algorithm that tackles both system and statistical heterogeneity to minimize the wall-…
College of Computer Science and Technology（计算机科学与技术学院）；Zhejiang University（浙江大学）
Federated Learning (FL) is a promising distributed learning paradigm, which allows a number of data owners (also called clients) to collaboratively learn a shared model without disclosing each client's data. However, FL may fail to proceed properly, amid a state that we call negative federated learning (NFL). This paper addresses the problem of negative federated learning. We formulate a rigorous definition of NFL and analyze its essential cause. We propose a novel framework called LINDT for tackling NFL in run-time. The framework can potentially work with any neural-network-based FL systems f…
Tackling Privacy Heterogeneity in Differentially Private Federated Learning
Department of Information Engineering, The Chinese University of Hong Kong（信息工程系，香港中文大学）；School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society（科学与工程学院，深圳人工智能与机器人社会研究院）
Department of Engineering, University of Palermo, Palermo, Italy（工程系，帕尔梅罗大学）；Department of Computer Science, Missouri University of Science and Technology, Rolla, USA（计算机科学系，密苏里科技大学）；Department of Computer Science, BITS-Pilani, Dubai, UAE（计算机科学系，比斯帕利尼学院）
The traditional approach in FL tries to learn a single global model collaboratively with the help of many clients under the orchestration of a central server. However, learning a single global model might not work well for all clients participating in the FL under data heterogeneity. Therefore, the personalization of the global model becomes crucial in handling the challenges that arise with statistical heterogeneity and the non-IID distribution of data. Unlike prior works, in this work we propose a new approach for obtaining a personalized model from a client-level objective. This further mot…
Local Gradient Regulation Stabilizes Federated Learning under Client Heterogeneity
National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, National University of Defense Technology（国家并行与分布式计算实验室，计算机科学与技术学院，国防科技大学）
Tackling Noisy Clients in Federated Learning with End-to-end Label Correction
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）
Tackling Heterogeneity in Federated Learning via Variance-Reduced Boltzmann Sampling within Homogeneous Social Coalitions
Department of Mathematical Sciences, Politecnico di Torino（数学科学系，都灵理工学院）；Istituto Nazionale di Fisica Nucleare, Sezione di Torino（国家核物理研究所，都灵分所）；Department of Electronics and Telecommunications, Politecnico di Torino（电子与电信系，都灵理工学院）
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
Institute of Statistics and Big Data, Renmin University of China（中国人民大学统计与大数据研究院）；Department of Statistics and Actuarial Science, University of Waterloo（滑铁卢大学统计与精算科学系）
The Hong Kong University of Science and Technology（香港科技大学）；The University of Hong Kong（香港大学）
The Federated Learning (FL) paradigm is known to face challenges under heterogeneous client data. Local training on non-iid distributed data results in deflected local optimum, which causes the client models drift further away from each other and degrades the aggregated global model's performance. A natural solution is to gather all client data onto the server, such that the server has a global view of the entire data distribution. Unfortunately, this reduces to regular training, which compromises clients' privacy and conflicts with the purpose of FL. In this paper, we put forth an idea to col…
HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning
University of Naples "Federico II"（那不勒斯腓特烈二世大学）；Queen Mary University of London（伦敦玛丽女王大学）；Brandenburg University of Technology Cottbus-Senftenberg（勃兰登堡工业大学）；Tallinn University of Technology（塔林理工大学）；University of Zanjan（赞詹大学）
In federated optimization, heterogeneity in the clients' local datasets and computation speeds results in large variations in the number of local updates performed by each client in each communication round. Naive weighted aggregation of such models causes objective inconsistency, that is, the global model converges to a stationary point of a mismatched objective function which can be arbitrarily different from the true objective. This paper provides a general framework to analyze the convergence of federated heterogeneous optimization algorithms. It subsumes previously proposed methods such a…
Hong Kong Baptist University（香港浸会大学）；The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
In federated learning (FL), model performance typically suffers from client drift induced by data heterogeneity, and mainstream works focus on correcting client drift. We propose a different approach named virtual homogeneity learning (VHL) to directly "rectify" the data heterogeneity. In particular, VHL conducts FL with a virtual homogeneous dataset crafted to satisfy two conditions: containing no private information and being separable. The virtual dataset can be generated from pure noise shared across clients, aiming to calibrate the features from the heterogeneous clients. Theoretically, w…
FedClust: Tackling Data Heterogeneity in Federated Learning through Weight-Driven Client Clustering
\ School of Computing；Informatics University of Louisiana at Lafayette 1 Th rv \"a ld Circle Lafayette, LA USA；\ School of Computer Science；Technology East China Normal University 1 Th rv \"a ld Circle Shanghai China；\ Department of Computer；Information Sciences University of Delaware 1 Th rv \"a ld Circle Newark, DE USA；School of Computing；Informatics University of Louisiana at Lafayette；School of Computer Science；Technology East China Normal University；Department of Computer；Information Sciences University of Delaware
FedCCA: Client-Centric Adaptation against Data Heterogeneity in Federated Learning on IoT Devices
Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）；Centre for Learning, Teaching, and Technology, The Education University of Hong Kong（香港教育大学学习、教学与技术中心）
Tackling Non-IIDness in HAPS-Aided Federated Learning
Non-Terrestrial Networks (NTN) Lab, Department of Systems and Computer Engineering, Carleton University（卡尔顿大学系统与计算机工程系非地面网络实验室）；School of EECS, Ohio University（俄亥俄大学电气工程与计算机科学学院）
Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks
Duke Kunshan University（昆山杜克大学）；Carnegie Mellon University（卡内基梅隆大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；IBM T. J. Watson Research Center（IBM T. J. 沃森研究中心）；Yale University（耶鲁大学）
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Federated learning (FL) is an emerging machine learning paradigm involving multiple clients, e.g., mobile phone devices, with an incentive to collaborate in solving a machine learning problem coordinated by a central server. FL was proposed in 2016 by Konečný et al. and McMahan et al. as a viable privacy-preserving alternative to traditional centralized machine learning since, by construction, the training data points are decentralized and never transferred by the clients to a central server. Therefore, to a certain degree, FL mitigates the privacy risks associated with centralized data collec…
Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）；Duke University（杜克大学）
Federated learning (FL) allows multiple clients to collaboratively train a deep learning model. One major challenge of FL is when data distribution is heterogeneous, i.e., differs from one client to another. Existing personalized FL algorithms are only applicable to narrow cases, e.g., one or two data classes per client, and therefore they do not satisfactorily address FL under varying levels of data heterogeneity. In this paper, we propose a novel framework, called DisTrans, to improve FL performance (i.e., model accuracy) via train and test-time distributional transformations along with a do…
Johns Hopkins University（约翰斯·霍普金斯大学）；Stanford University（斯坦福大学）；UC Santa Cruz（加州大学圣克鲁兹分校）；Carnegie Mellon University（卡内基梅隆大学）
Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental challenges such as the lack of convergence and the potential for catastrophic forgetting across real-world heterogeneous devices. In this paper, we demonstrate that self-attention-based architectures (e.g., Transformers) are more robust to distribution shifts and hence improve federated learning over heterogeneous data. Concretely, we conduct the first rigoro…
Tackling Data Heterogeneity in Federated Learning via Loss Decomposition
School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学网络空间学院）；New H3C Technologies Co., Ltd.（新华三技术有限公司）；Computer Science and Engineering, University of California, Santa Cruz（加州大学圣克鲁兹分校计算机科学与工程系）；Department of Statistics and Actuarial Science, The University of Hong Kong（香港大学统计与精算科学系）
Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
Duke University（杜克大学）；University of Maryland, College Park（马里兰大学帕克分校）；George Mason University（乔治梅森大学）；Yale University（耶鲁大学）；The State University of New York at Buffalo（纽约州立大学布法罗分校）
Initialization Is Critical: Advancing Federated Short-Term Load Forecasting under Load Heterogeneity via Model Initialization
School of Electrical Engineering and Computer Science, The Pennsylvania State University（宾夕法尼亚州立大学电气工程与计算机科学学院）；Department of Electrical and Computer Engineering, Bucknell University（巴克内尔大学电气与计算机工程系）
UC Santa Barbara（加州大学圣巴巴拉分校）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Pennsylvania（宾夕法尼亚大学）
Federated Learning is a novel paradigm that involves learning from data samples distributed across a large network of clients while the data remains local. It is, however, known that federated learning is prone to multiple system challenges including system heterogeneity where clients have different computation and communication capabilities. Such heterogeneity in clients' computation speeds has a negative effect on the scalability of federated learning algorithms and causes significant slow-down in their runtime due to the existence of stragglers. In this paper, we propose a novel straggler-r…
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 Momentum (FedCM), to tackle problems of partial participation and client heterogeneity in real-world federated learning applications. FedCM aggregates global gradient information in previous communication rounds and modifies client gradient descent with a momentum-like term, which can effectively correct the bias and improve the stability of local SGD. We provide theoretical analysis …
Shanghai Jiao Tong University（上海交通大学）；Meta Platforms（元平台公司）；Shanghai AI Laboratory（上海人工智能实验室）；Weizmann Institute of Science（魏茨曼科学研究所）
One of the key challenges in federated learning (FL) is local data distribution heterogeneity across clients, which may cause inconsistent feature spaces across clients. To address this issue, we propose a novel method FedFM, which guides each client's features to match shared category-wise anchors (landmarks in feature space). This method attempts to mitigate the negative effects of data heterogeneity in FL by aligning each client's feature space. Besides, we tackle the challenge of varying objective function and provide convergence guarantee for FedFM. In FedFM, to mitigate the phenomenon of…
Federated learning (FL) is a distributed machine learning paradigm that allows clients to collaboratively train a model over their own local data. FL promises the privacy of clients and its security can be strengthened by cryptographic methods such as additively homomorphic encryption (HE). However, the efficiency of FL could seriously suffer from the statistical heterogeneity in both the data distribution discrepancy among clients and the global distribution skewness. We mathematically demonstrate the cause of performance degradation in FL and examine the performance of FL over various datase…
Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Waterloo（滑铁卢大学）
Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models. In this setting, one major obstacle is data heterogeneity, i.e., each client having non-identically and independently distributed (non-IID) data. This is analogous to the context of Domain Generalization (DG), where each client can be treated as a different domain. However, while many approaches in DG tackle data heterogeneity from the algorithmic perspective, recent evidence suggests that data augmentation can induce equal or greater per…
