Federated learning (FL) often degrades when clients hold heterogeneous non-Independent and Identically Distributed (non-IID) data and when some clients behave adversarially, leading to client drift, slow convergence, and high communication overhead. This paper proposes FedEMA-Distill, a server-side procedure that combines an exponential moving average (EMA) of the global model with ensemble knowledge distillation from client-uploaded prediction logits evaluated on a small public proxy dataset. Clients run standard local training, upload only compressed logits, and may use different model architectures, so no changes are required to client-side software while still supporting model heterogeneity across devices. Experiments on CIFAR-10, CIFAR-100, FEMNIST, and AG News under Dirichlet-0.1 label skew show that FedEMA-Distill improves top-1 accuracy by several percentage points (up to +5% on CIFAR-10 and +6% on CIFAR-100) over representative baselines, reaches a given target accuracy in 30-35% fewer communication rounds, and reduces per-round client uplink payloads to 0.09-0.46 MB, i.e., roughly an order of magnitude less than transmitting full model weights. Using coordinate-wise median or trimmed-mean aggregation of logits at the server further stabilizes training in the presence of up to 10-20% Byzantine clients and yields well-calibrated predictions under attack. These results indicate that coupling temporal smoothing with logits-only aggregation provides a communication-efficient and attack-resilient FL pipeline that is deployment-friendly and compatible with secure aggregation and differential privacy, since only aggregated or obfuscated model outputs are exchanged.
FedEMA: Federated Exponential Moving Averaging with Negative Entropy Regularizer in Autonomous Driving
Department of Electrical and Electronic Engineering, The University of Hong Kong（香港大学电子与电气工程系）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；Shenzhen International Center For Industrial And Applied Mathematics, Shenzhen Research Institute of Big Data（深圳国际工业与应用数学中心、深圳大数据研究 institute）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）
Improving Communication Efficiency of Federated Distillation via Accumulating Local Updates
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）；Zhongguancun Laboratory（中关村实验室）；Beijing Jiaotong University（北京交通大学）
针对联邦蒸馏的通信开销问题，本文提出 ALU 方法，通过累积多轮本地更新后再向中央服务器传输知识，降低通信频率并显著提升通信效率。
Self-supervised learning (SSL) is capable of learning remarkable representations from centrally available data. Recent works further implement federated learning with SSL to learn from rapidly growing decentralized unlabeled images (e.g., from cameras and phones), often resulted from privacy constraints. Extensive attention has been paid to SSL approaches based on Siamese networks. However, such an effort has not yet revealed deep insights into various fundamental building blocks for the federated self-supervised learning (FedSSL) architecture. We aim to fill in this gap via in-depth empirical…
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally different communication properties, emerged. FD methods leverage ensemble distillation techniques and exchange model outputs, presented as soft labels on an unlabeled public data set, between the central server and the participating clients. While for conventional Federated Learning algorithms, like Federated Averaging (FA), communication scales with the size of th…
MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；National Engineering Research Center for Software Engineering, Peking University（北京大学国家软件工程研究中心）；State University of New York at Buffalo（纽约州立大学布法罗分校）
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
Federated learning suffers in the case of non-iid local datasets, i.e., when the distributions of the clients' data are heterogeneous. One promising approach to this challenge is the recently proposed method FedAUX, an augmentation of federated distillation with robust results on even highly heterogeneous client data. FedAUX is a partially $(ε, δ)$-differentially private method, insofar as the clients' private data is protected in only part of the training it takes part in. This work contributes a fully differentially private modification, termed FedAUXfdp. We further contribute an upper bound…
Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·扎耶德人工智能大学）；International School, Beijing University of Posts and Telecommunications（北京邮电大学国际学院）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系）
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 …
Korea Advanced Institute of Science and Technology（韩国科学技术院）；King’s College London（伦敦国王学院）
Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels. This work studies some of the opportunities and challenges arising from the presence of wireless communication links. We specifically consider wireless implementations of Federated Learning (FL) and Federated Distillation (FD), as well as of a novel Hybrid Federated Distillation (HFD) scheme. Both digital implementations based on separate source-channel coding and over-the-air computing implementations based on joint source-channel coding are proposed and evaluated over Ga…
Robust Decentralized Federated Distillation via Multi-Modality Knowledge Collaboration
Faculty of Applied Sciences, Macao Polytechnic University（澳门理工大学应用科学学院）；School of Engineering and Technology, Central Queensland University（中央昆士兰大学工程与技术学院）；School of Information and Communication Technology, Griffith University（格里菲斯大学信息与通信技术学院）
University of Florida（佛罗里达大学）；Cognization Lab（认知实验室）
Current federated learning algorithms take tens of communication rounds transmitting unwieldy model weights under ideal circumstances and hundreds when data is poorly distributed. Inspired by recent work on dataset distillation and distributed one-shot learning, we propose Distilled One-Shot Federated Learning (DOSFL) to significantly reduce the communication cost while achieving comparable performance. In just one round, each client distills their private dataset, sends the synthetic data (e.g. images or sentences) to the server, and collectively trains a global model. The distilled data look…
Google LLC（谷歌有限责任公司）；University of Washington（华盛顿大学）
We trained a keyword spotting model using federated learning on real user devices and observed significant improvements when the model was deployed for inference on phones. To compensate for data domains that are missing from on-device training caches, we employed joint federated-centralized training. And to learn in the absence of curated labels on-device, we formulated a confidence filtering strategy based on user-feedback signals for federated distillation. These techniques created models that significantly improved quality metrics in offline evaluations and user-experience metrics in live …
University at Buffalo（布法罗大学）；United Imaging Intelligence（联影智能）
Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. …
Yonsei University（延世大学）；Deakin University（迪肯大学）；Samsung Research, Samsung Electronics（三星电子三星研究院）；University of Oulu（奥卢大学）
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a server in the uplink as in federated distillation (FD), whereas global model parameters are downloaded in the downlink as in federated learning (FL). This requires a model output-to-parameter conversion at the server, after collecting additional data samples from devices. To preserve privacy while not compromising accuracy, linearly mixed-up local samples are uploaded, and inverse…
Knowledge distillation has recently become popular as a method of model aggregation on the server for federated learning. It is generally assumed that there are abundant public unlabeled data on the server. However, in reality, there exists a domain discrepancy between the datasets of the server domain and a client domain, which limits the performance of knowledge distillation. How to improve the aggregation under such a domain discrepancy setting is still an open problem. In this paper, we first analyze the generalization bound of the aggregation model produced from knowledge distillation for…
Federated learning (FL) is a decentralized privacy-preserving learning technique in which clients learn a joint collaborative model through a central aggregator without sharing their data. In this setting, all clients learn a single common predictor (FedAvg), which does not generalize well on each client's local data due to the statistical data heterogeneity among clients. In this paper, we address this problem with PersFL, a discrete two-stage personalized learning algorithm. In the first stage, PersFL finds the optimal teacher model of each client during the FL training phase. In the second …
Dataset Distillation-based Hybrid Federated Learning on Non-IID Data
College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China（浙江工业大学信息工程学院，杭州 310023，中国）；Zhejiang Key Laboratory of Intelligent Perception and Control for Complex Systems, Hangzhou, China（浙江省复杂系统智能感知与控制重点实验室，杭州，中国）；College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China（浙江大学控制科学与工程学院，杭州 310027，中国）；Computing Science and Internet of Things, Newcastle University, NE1 7RU Newcastle, UK（新castle大学计算科学与物联网学院，NE1 7RU Newcastle, UK）
Framework for Co-distillation Driven Federated Learning to Address Class Imbalance in Healthcare
Indian Institute of Technology, Bombay（印度理工学院孟买分校）；Sardar Patel Institute of Technology（萨达尔·帕特尔理工学院）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）
Xiamen University（厦门大学）；Hong Kong Baptist University（香港浸会大学）
Federated learning provides a privacy guarantee for generating good deep learning models on distributed clients with different kinds of data. Nevertheless, dealing with non-IID data is one of the most challenging problems for federated learning. Researchers have proposed a variety of methods to eliminate the negative influence of non-IIDness. However, they only focus on the non-IID data provided that the universal class distribution is balanced. In many real-world applications, the universal class distribution is long-tailed, which causes the model seriously biased. Therefore, this paper studi…
Personalized Federated Learning via Backbone Self-Distillation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, UCAS（中国科学院大学网络空间安全学院）；School of Communication and Information Engineering, Shanghai University（上海大学通信与信息工程学院）；School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）
Learning Critically: Selective Self Distillation in Federated Learning on Non-IID Data
Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences and the University of Chinese Academy of Sciences（北京移动计算与 pervasive 设备重点实验室，计算技术研究所，中国科学院和中国科学院大学）；Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences（北京移动计算与 pervasive 设备重点实验室，计算技术研究所，中国科学院）；Shandong Academy of Intelligent Computing Technology（山东省智能计算技术研究院）；Frontier Sciences and Education, Chinese Academy of Sciences（前沿科学与教育，中国科学院）
Graduate School of Informatics, Kyoto University（京都大学信息学研究科）
This study develops a federated learning (FL) framework overcoming largely incremental communication costs due to model sizes in typical frameworks without compromising model performance. To this end, based on the idea of leveraging an unlabeled open dataset, we propose a distillation-based semi-supervised FL (DS-FL) algorithm that exchanges the outputs of local models among mobile devices, instead of model parameter exchange employed by the typical frameworks. In DS-FL, the communication cost depends only on the output dimensions of the models and does not scale up according to the model size…
Mohammed VI Polytechnic University（穆罕默德六世理工大学）；New York University (NYU) Abu Dhabi（纽约大学阿布扎比分校）；NYU Tandon School of Engineering（纽约大学坦登工程学院）
Federated distillation (FD) paradigm has been recently proposed as a promising alternative to federated learning (FL) especially in wireless sensor networks with limited communication resources. However, all state-of-the art FD algorithms are designed for only classification tasks and less attention has been given to regression tasks. In this work, we propose an FD framework that properly operates on regression learning problems. Afterwards, we present a use-case implementation by proposing an indoor localization system that shows a good trade-off communication load vs. accuracy compared to fe…
The Hong Kong University of Science and Technology（香港科技大学）
Federated learning (FL) is a promising paradigm to enable privacy-preserving deep learning from distributed data. Most previous works are based on federated average (FedAvg), which, however, faces several critical issues, including a high communication overhead and the difficulty in dealing with heterogeneous model architectures. Federated Distillation (FD) is a recently proposed alternative to enable communication-efficient and robust FL, which achieves orders of magnitude reduction of the communication overhead compared with FedAvg and is flexible to handle heterogeneous models at the client…
FedCC: Towards Addressing Label Distribution Skews in Distillation-Based Federated Learning
Huawei Heisenberg Research Center, Huawei Technologies Duesseldorf GmbH（华为海森堡研究中心（华为技术有限公司杜塞尔多夫分部））；TUM School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）
Conventional federated learning directly averages model weights, which is only possible for collaboration between models with homogeneous architectures. Sharing prediction instead of weight removes this obstacle and eliminates the risk of white-box inference attacks in conventional federated learning. However, the predictions from local models are sensitive and would leak training data privacy to the public. To address this issue, one naive approach is adding the differentially private random noise to the predictions, which however brings a substantial trade-off between privacy budget and mode…
Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face are heterogeneity in data across clients and collaboration of clients with {\em diverse resources}. In this work, we introduce a \textit{quantized} and \textit{personalized} FL algorithm QuPeD that facilitates collective (personalized model compression) training via \textit{knowledge distillation} (KD) among clients who have access to heterogeneous data and resources. For personalization, we allow clients to learn \…
FedAFD: Multimodal Federated Learning via Adversarial Fusion and Distillation
Zhejiang Key Laboratory of Space Information Sensing and Transmission, Hangzhou Dianzi University（浙江空间信息感知与传输重点实验室，杭州电子大学）；Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University（复杂系统建模与仿真实验室，计算机科学与技术学院，杭州电子大学）；Alibaba International Digital Commerce Group（阿里巴巴国际数字商业集团）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）
This paper proposes a fully decentralized federated learning (FL) scheme for Internet of Everything (IoE) devices that are connected via multi-hop networks. Because FL algorithms hardly converge the parameters of machine learning (ML) models, this paper focuses on the convergence of ML models in function spaces. Considering that the representative loss functions of ML tasks e.g, mean squared error (MSE) and Kullback-Leibler (KL) divergence, are convex functionals, algorithms that directly update functions in function spaces could converge to the optimal solution. The key concept of this paper …
Federated Learning via Input-Output Collaborative Distillation
University at Buffalo（布法罗大学）；Institute of Artificial Intelligence, Beihang University（北京航空航天大学人工智能研究院）；Harvard Medical School（哈佛医学院）；Virginia Tech（弗吉尼亚理工大学）；Jarvis Research Center, Tencent YouTu Lab（腾讯优图实验室杰瑞斯研究中心）；United Imaging Intelligence（联影智能）；Hangzhou Research Institute, Beihang University（北京航空航天大学杭州研究院）；Zhongguancun Laboratory（中关村实验室）；Nanchang Institute of Technology（南昌工学院）
Spectral Co-Distillation for Personalized Federated Learning
Singapore University of Technology and Design (SUTD)（新加坡科技设计大学）；Zhejiang University/University of Illinois Urbana-Champaign Institute, Zhejiang University（浙江大学伊利诺伊大学厄巴纳-香槟校区联合学院，浙江大学）
Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the parameters of the server model and the updated parameters from the client side. However, directly averaging model parameters is only possible if all models have the same structure and size, which could be a restrictive constraint in many scenarios. In this work we investigate more powerful and more flexible aggregation schemes for FL. Specifical…
