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 as FedAvg and FedProx and provides the first principled understanding of the solution bias and the convergence slowdown due to objective inconsistency. Using insights from this analysis, we propose FedNova, a normalized averaging method that eliminates objective inconsistency while preserving fast error convergence.
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）
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…
Secure aggregation is a cryptographic protocol that securely computes the aggregation of its inputs. It is pivotal in keeping model updates private in federated learning. Indeed, the use of secure aggregation prevents the server from learning the value and the source of the individual model updates provided by the users, hampering inference and data attribution attacks. In this work, we show that a malicious server can easily elude secure aggregation as if the latter were not in place. We devise two different attacks capable of inferring information on individual private training datasets, ind…
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…
University of Science and Technology of China (USTC)（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
Attributes skew hinders the current federated learning (FL) frameworks from consistent optimization directions among the clients, which inevitably leads to performance reduction and unstable convergence. The core problems lie in that: 1) Domain-specific attributes, which are non-causal and only locally valid, are indeliberately mixed into global aggregation. 2) The one-stage optimizations of entangled attributes cannot simultaneously satisfy two conflicting objectives, i.e., generalization and personalization. To cope with these, we proposed disentangled federated learning (DFL) to disentangle…
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）
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 (FL) has gain growing interests for its capability of learning from distributed data sources collectively without the need of accessing the raw data samples across different sources. So far FL research has mostly focused on improving the performance, how the algorithmic disparity will be impacted for the model learned from FL and the impact of algorithmic disparity on the utility inconsistency are largely unexplored. In this paper, we propose an FL framework to jointly consider performance consistency and algorithmic fairness across different local clients (data sources). We…
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）
Viterbi School of Engineering（维特比工程学院）；University of Southern California（南加利福尼亚大学）
Federated Learning (FL) is transforming the ML training ecosystem from a centralized over-the-cloud setting to distributed training over edge devices in order to strengthen data privacy. An essential but rarely studied challenge in FL is label deficiency at the edge. This problem is even more pronounced in FL compared to centralized training due to the fact that FL users are often reluctant to label their private data. Furthermore, due to the heterogeneous nature of the data at edge devices, it is crucial to develop personalized models. In this paper we propose self-supervised federated learni…
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）
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 c…
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-…
Stanford University（斯坦福大学）；The University of Hong Kong（香港大学）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
The collection and curation of large-scale medical datasets from multiple institutions is essential for training accurate deep learning models, but privacy concerns often hinder data sharing. Federated learning (FL) is a promising solution that enables privacy-preserving collaborative learning among different institutions, but it generally suffers from performance deterioration due to heterogeneous data distributions and a lack of quality labeled data. In this paper, we present a robust and label-efficient self-supervised FL framework for medical image analysis. Our method introduces a novel T…
FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；The Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；The Guangdong Provincial Key Laboratory of Future Networks of Intelligence（广东省未来智能网络重点实验室）；Research Center for Industries of the Future, Westlake University（西湖大学未来产业研究中心）；School of Engineering, Westlake University（西湖大学工程学院）
FedMAC: Tackling Partial-Modality Missing in Federated Learning with Cross-Modal Aggregation and Contrastive Regularization
Hanoi University of Science and Technology（河内科学技术大学）；Nagoya University（名古屋大学）；Washington State University（华盛顿州立大学）；Swiss Federal Institute of Technology Lausanne（洛桑联邦理工学院）
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
The federated learning (FL) framework trains a machine learning model using decentralized data stored at edge client devices by periodically aggregating locally trained models. Popular optimization algorithms of FL use vanilla (stochastic) gradient descent for both local updates at clients and global updates at the aggregating server. Recently, adaptive optimization methods such as AdaGrad have been studied for server updates. However, the effect of using adaptive optimization methods for local updates at clients is not yet understood. We show in both theory and practice that while local adapt…
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）
Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Zhongguancun Laboratory（中关村实验室）；Sichuan University（四川大学）；University at Buffalo（纽约州立大学布法罗分校）
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）
University of California, Davis（加利福尼亚大学戴维斯分校）；Google（谷歌公司）
With more regulations tackling users' privacy-sensitive data protection in recent years, access to such data has become increasingly restricted and controversial. To exploit the wealth of data generated and located at distributed entities such as mobile phones, a revolutionary decentralized machine learning setting, known as Federated Learning, enables multiple clients located at different geographical locations to collaboratively learn a machine learning model while keeping all their data on-device. However, the scale and decentralization of federated learning present new challenges. Communic…
Federated learning (FL) aims to train machine learning models in the decentralized system consisting of an enormous amount of smart edge devices. Federated averaging (FedAvg), the fundamental algorithm in FL settings, proposes on-device training and model aggregation to avoid the potential heavy communication costs and privacy concerns brought by transmitting raw data. However, through theoretical analysis we argue that 1) the multiple steps of local updating will result in gradient biases and 2) there is an inconsistency between the expected target distribution and the optimization objectives…
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；Sony AI（索尼人工智能研究院）；Huawei Cloud & AI（华为云与计算）
The statistical heterogeneity of the non-independent and identically distributed (non-IID) data in local clients significantly limits the performance of federated learning. Previous attempts like FedProx, SCAFFOLD, MOON, FedNova and FedDyn resort to an optimization perspective, which requires an auxiliary term or re-weights local updates to calibrate the learning bias or the objective inconsistency. However, in addition to previous explorations for improvement in federated averaging, our analysis shows that another critical bottleneck is the poorer optima of client models in more heterogeneous…
On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond
University of Electronic Science and Technology of China（电子科技大学）；Fudan University（复旦大学）；Harbin Institute of Technology Shenzhen（哈尔滨工业大学（深圳））；Meta AI；Chinese University of Hong Kong Shenzhen（香港中文大学（深圳））
Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization
School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University（中山大学计算机科学与技术学院深圳校区）；School of Computer Science Faculty of Engineering The University of Sydney（悉尼大学计算机科学学院）；Generative AI Lab College of Computing and Data Science Nanyang Technological University（南洋理工大学计算与数据科学学院生成式人工智能实验室）
Federated Learning with Manifold Regularization and Normalized Update Reaggregation
School of Information and Electronics, Beijing Institute of Technology（北京理工大学信息与电子学院）；JD Explore Academy（京东探索研究院）；School of Computer Science, Wuhan University（武汉大学计算机学院）
Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
College of Computer Science, Zhejiang University（浙江大学计算机学院）；Tiansuan Lab, Ant Group（蚂蚁集团天算实验室）；College of Computer and Data Science, Fuzhou University（福州大学计算机与大数据学院）
A critical challenge of federated learning is data heterogeneity and imbalance across clients, which leads to inconsistency between local networks and unstable convergence of global models. To alleviate the limitations, we propose a novel architectural regularization technique that constructs multiple auxiliary branches in each local model by grafting local and global subnetworks at several different levels and that learns the representations of the main pathway in the local model congruent to the auxiliary hybrid pathways via online knowledge distillation. The proposed technique is effective …
The Hong Kong Polytechnic University（香港理工大学）；Huazhong University of Science and Technology（华中科技大学）；Michigan State University（密歇根州立大学）；Hohai University（河海大学）
In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources. It is well acknowledged that step asynchronism leads to objective inconsistency under non-i.i.d. data, which degrades the model's accuracy. To address this issue, we propose a new algorithm FedaGrac, which calibrates the local direction to a predictive global orientation. Taking advantage of the estimated orientation, we guarantee that the aggregated model does not excessively deviate…
In real-world federated learning scenarios, participants could have their own personalized labels which are incompatible with those from other clients, due to using different label permutations or tackling completely different tasks or domains. However, most existing FL approaches cannot effectively tackle such extremely heterogeneous scenarios since they often assume that (1) all participants use a synchronized set of labels, and (2) they train on the same task from the same domain. In this work, to tackle these challenges, we introduce Factorized-FL, which allows to effectively tackle label-…
In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models. Although this precludes the need to access clients' data directly, the global model's convergence often suffers from data heterogeneity. This study starts from an analogy to continual learning and suggests that forgetting could be the bottleneck of federated learning. We observe that the global model forgets the knowledge from previous rounds, and the local training induces forgetting the knowledge outside of the local distribution. Based on our findings, we hypothesize that …
Princeton University（普林斯顿大学）；Institute for Advanced Study（高等研究院）
An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural language understanding tasks. It requires all participants to add a simple encryption step to prevent an eavesdropping attacker from recovering private text data. Such an encryption step is efficient and only affects the task performance slightly. In addition, TextHide fits well with the popular framework of fine-tuning pre-trained language models (e.g., BERT) fo…
Auburn University（奥本大学）；Sony AI（索尼人工智能）；Baidu Research（百度研究院）；University of Oregon（俄勒冈大学）
The federated learning (FL) framework enables edge clients to collaboratively learn a shared inference model while keeping privacy of training data on clients. Recently, many heuristics efforts have been made to generalize centralized adaptive optimization methods, such as SGDM, Adam, AdaGrad, etc., to federated settings for improving convergence and accuracy. However, there is still a paucity of theoretical principles on where to and how to design and utilize adaptive optimization methods in federated settings. This work aims to develop novel adaptive optimization methods for FL from the pers…
