An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to the fact that client devices have different system capabilities. A considerable number of federated optimization methods address this challenge. In the literature, empirical evaluations usually start federated training from random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task that can be used to pre-train a model before starting federated training. We empirically study the impact of starting from a pre-trained model in federated learning using four standard federated learning benchmark datasets. Unsurprisingly, starting from a pre-trained model reduces the training time required to reach a target error rate and enables the training of more accurate models (up to 40\%) than is possible when starting from random initialization. Surprisingly, we also find that starting federated learning from a pre-trained initialization reduces the effect of both data and system heterogeneity. We recommend that future work proposing and evaluating federated optimization methods evaluate the performance when starting from random and pre-trained initializations. We also believe this study raises several questions for further work on understanding the role of heterogeneity in federated optimization.
An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to client devices having different system capabilities. A considerable number of federated optimization methods address this challenge. In the literature, empirical evaluations usually start federated training from random initialization. However, in many practical applications of federated learning, the server has access to proxy data for the training task that can…
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）
SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning
Georgia Institute of Technology（佐治亚理工学院）；TReNDS Center（TReNDS中心）；Google DeepMind, Mila - Quebec AI Institute（谷歌DeepMind、魁北克AI研究所）；Georgia State University（佐治亚州立大学）；Emory University（埃默里大学）；Center for Translational Research in Neuroimaging & Data Science (TReNDS)（神经影像与数据科学转化研究中心（TReNDS））
Rethinking Personalized Reward Modeling for LLMs under Preference Heterogeneity via Group-Debiased Federated Learning
Institute of Engineering Research, Korea University（韩国大学工程研究所）；Kim Jaechul Graduate School of AI, KAIST（韩国科学技术院金在哲人工智能研究生院）；Industrial Management Engineering, Korea University（韩国大学产业管理工程学院）
Tsinghua University（清华大学）；BNRist（北京国家研究院（BNRist））；Key Laboratory of Pervasive Computing, Ministry of Education（教育部普适计算重点实验室）
Federated learning (FL) refers to the learning paradigm that trains machine learning models directly in the decentralized systems consisting of smart edge devices without transmitting the raw data, which avoids the heavy communication costs and privacy concerns. Given the typical heterogeneous data distributions in such situations, the popular FL algorithm \emph{Federated Averaging} (FedAvg) suffers from weight divergence and thus cannot achieve a competitive performance for the global model (denoted as the \emph{initial performance} in FL) compared to centralized methods. In this paper, we pr…
We address the problem of federated learning (FL) where users are distributed and partitioned into clusters. This setup captures settings where different groups of users have their own objectives (learning tasks) but by aggregating their data with others in the same cluster (same learning task), they can leverage the strength in numbers in order to perform more efficient federated learning. For this new framework of clustered federated learning, we propose the Iterative Federated Clustering Algorithm (IFCA), which alternately estimates the cluster identities of the users and optimizes model pa…
Improving Learning of New Diseases through Knowledge-Enhanced Initialization for Federated Adapter Tuning
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所（IHPC），科技研究局（A*STAR））；EVYD Technology（EVYD技术）
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）
The idea of federated learning is to train deep neural network models collaboratively and share them with multiple participants without exposing their private training data to each other. This is highly attractive in the medical domain due to patients' privacy records. However, a recently proposed method called Deep Leakage from Gradients enables attackers to reconstruct data from shared gradients. This study shows how easy it is to reconstruct images for different data initialization schemes and distance measures. We show how data and model architecture influence the optimal choice of initial…
Federated learning (FL) is recently surging as a promising decentralized deep learning (DL) framework that enables DL-based approaches trained collaboratively across clients without sharing private data. However, in the context of the central party being active and dishonest, the data of individual clients might be perfectly reconstructed, leading to the high possibility of sensitive information being leaked. Moreover, FL also suffers from the nonindependent and identically distributed (non-IID) data among clients, resulting in the degradation in the inference performance on local clients' dat…
Halıcıoğlu Data Science Institute（哈利西奥卢数据科学研究所）；UC San Diego（加州大学圣地亚哥分校）
In this paper, we address the dichotomy between heterogeneous models and simultaneous training in Federated Learning (FL) via a clustering framework. We define a new clustering model for FL based on the (optimal) local models of the users: two users belong to the same cluster if their local models are close; otherwise they belong to different clusters. A standard algorithm for clustered FL is proposed in \cite{ghosh_efficient_2021}, called \texttt{IFCA}, which requires \emph{suitable} initialization and the knowledge of hyper-parameters like the number of clusters (which is often quite difficu…
PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark
Shanghai Jiao Tong University（上海交通大学）；Institute for AI Industry Research, Tsinghua University（清华大学人工智能产业研究院）；Queen’s University Belfast（贝尔法斯特女王大学）；Stevens Institute of Technology（史蒂文斯理工学院）
OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement
National University of Defense Technology（国防科技大学）；Hebei University of Technology（河北工业大学）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区网络空间科学与技术学院）
Federated learning, which solves the problem of data island by connecting multiple computational devices into a decentralized system, has become a promising paradigm for privacy-preserving machine learning. This paper studies vertical federated learning (VFL), which tackles the scenarios where collaborating organizations share the same set of users but disjoint features. Contemporary VFL methods are mainly used in static scenarios where the active party and the passive party have all the data from the beginning and will not change. However, the data in real life often changes dynamically. To a…
On the Limits of Momentum in Decentralized and Federated Optimization
Department of Computer and Control Engineering, Polytechnic of Turin（计算机与控制工程系，都灵理工学院）；Thomas Lord Department of Computer Science, USC Viterbi School of Engineering（托马斯·劳德计算机科学系，USC维特里商学院）
Local K-Similarity Constraint for Federated Learning with Label Noise
NAAMII, Nepal Applied Mathematics and Informatics Institute for Research（NAAMII尼泊尔应用数学与信息学研究所）；Rochester Institute of Technology（罗切斯特技术研究所）；West Virginia University（西弗吉尼亚大学）；University of Lausanne（洛桑大学）；Ulsan National Institute of Science & Technology（釜山国家科学与技术研究所）；University of Aberdeen（阿伯丁大学）
DecHW: Heterogeneous Decentralized Federated Learning Exploiting Second-Order Information
School of Information Technology, Deakin University（德肯大学信息科技学院）；Institute for Informatics and Telematics (IIT), Italian National Research Council (CNR)（信息与电信学研究院（IIT），意大利国家研究委员会（CNR））
Northeastern University（东北大学）；The Fuqua School of Business（福库商学院）；Duke University（杜克大学）；Center for Statistical Science（统计科学中心）；Tsinghua University（清华大学）
This paper studies the problem of model training under Federated Learning when clients exhibit cluster structure. We contextualize this problem in mixed regression, where each client has limited local data generated from one of $k$ unknown regression models. We design an algorithm that achieves global convergence from any initialization, and works even when local data volume is highly unbalanced -- there could exist clients that contain $O(1)$ data points only. Our algorithm first runs moment descent on a few anchor clients (each with $\tildeΩ(k)$ data points) to obtain coarse model estimates.…
Federated Learning (FL) is an increasingly popular machine learning paradigm in which multiple nodes try to collaboratively learn under privacy, communication and multiple heterogeneity constraints. A persistent problem in federated learning is that it is not clear what the optimization objective should be: the standard average risk minimization of supervised learning is inadequate in handling several major constraints specific to federated learning, such as communication adaptivity and personalization control. We identify several key desiderata in frameworks for federated learning and introdu…
Towards One-shot Federated Learning: Advances, Challenges, and Future Directions
Department of Electrical Engineering and Information Technology, University of Naples Federico II（那不勒斯费德里科二世大学电气工程与信息科技系）；Department of Mathematics and Applications "R. Caccioppoli", University of Naples Federico II（那不勒斯费德里科二世大学数学与应用系）；Department of Mathematics, Indian Institute of Technology Indore（印度理工学院Indore分校数学系）
FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning
University of Helsinki（赫尔辛基大学）；Zhejiang University（浙江大学）；Simon Fraser University（西蒙菲莎大学）；Norwegian University of Science and Technology（挪威科技大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning, which achieves training performance competitive to prior parameter averaging based methods, while additionally allowing the clients to train different model architectures, by distilling the client predictions on an unlabeled auxiliary set of data into a student model. In this work we propose FedAUX, an extension to FD, which, under the same set of assumptions, drastically improves performance by deriving maximum utility from the unlabeled auxiliary data. FedAUX modifies the FD training procedure in two …
University of Stavanger（斯塔万格大学）；RWTH-Aachen University（亚琛工业大学）；University of Cologne（科隆大学）
Unlike traditional central training, federated learning (FL) improves the performance of the global model by sharing and aggregating local models rather than local data to protect the users' privacy. Although this training approach appears secure, some research has demonstrated that an attacker can still recover private data based on the shared gradient information. This on-the-fly reconstruction attack deserves to be studied in depth because it can occur at any stage of training, whether at the beginning or at the end of model training; no relevant dataset is required and no additional models…
Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
VinUni-Illinois Smart Health Center（VinUni-Illinois智能健康中心）；College of Engineering & Computer Science（工程与计算机科学学院）；University of Notre Dame（诺特丹大学）；Technische Universität Berlin（柏林技术大学）
Contrastive Federated Learning with Tabular Data Silos
The University of Queensland（昆士兰大学）；Monash University（莫纳什大学）；Indonesia Taxation Office（印度尼西亚税务局）；Queensland University of Technology（昆士兰科技大学）；SUNY Albany（纽约州立大学奥尔巴尼分校）；Dartmouth College（达特茅斯学院）；Hong Kong Polytechnic University（香港理工大学）；Renmin University of China（中国人民大学）
University of California San Diego（加州大学圣地亚哥分校）；Czech Technical University（捷克技术大学）；UCF（中佛罗里达大学）
An oft-cited open problem of federated learning is the existence of data heterogeneity at the clients. One pathway to understanding the drastic accuracy drop in federated learning is by scrutinizing the behavior of the clients' deep models on data with different levels of "difficulty", which has been left unaddressed. In this paper, we investigate a different and rarely studied dimension of FL: ordered learning. Specifically, we aim to investigate how ordered learning principles can contribute to alleviating the heterogeneity effects in FL. We present theoretical analysis and conduct extensive…
