我们提出了FedDM，一个专为扩散模型联邦训练设计的新型训练框架。我们的理论分析确立了扩散模型在联邦设置下训练时的收敛性，并给出了保证该收敛性的具体条件。我们提出了一套利用U-Net架构作为扩散模型骨干的训练算法，包括基础的联邦平均变体FedDM-vanilla、用于处理客户端间数据异构性的FedDM-prox，以及引入量化模块以减小模型更新大小、从而提升联邦网络通信效率的FedDM-quant。我们在FashionMNIST（28x28分辨率）、CIFAR-10（32x32分辨率）和CelebA（64x64分辨率）上对DDPM进行了算法评估，并在LSUN Church Outdoors（256x256分辨率）上对LDM进行了评估，仅关注成像模态。评估结果表明，FedDM算法在不同图像分辨率下均保持了较高的生成质量。同时，在局部训练目标中使用量化更新和近端项显著提升了通信效率（最高达4倍）和模型收敛性，尤其在非独立同分布（non-IID）数据设置下，但代价是FID分数增加（最高达1.75倍）。
英文摘要：
We introduce FedDM, a novel training framework designed for the federated training of diffusion models. Our theoretical analysis establishes the convergence of diffusion models when trained in a federated setting, presenting the specific conditions under which this convergence is guaranteed. We propose a suite of training algorithms that leverage the U-Net architecture as the backbone for our diffusion models. These include a basic Federated Averaging variant, FedDM-vanilla, FedDM-prox to handle data heterogeneity among clients, and FedDM-quant, which incorporates a quantization module to reduce the model update size, thereby enhancing communication efficiency across the federated network.
We evaluate our algorithms on FashionMNIST (28x28 resolution), CIFAR-10 (32x32 resolution), and CelebA (64x64 resolution) for DDPMs, as well as LSUN Church Outdoors (256x256 resolution) for LDMs, focusing exclusively on the imaging modality. Our evaluation results demonstrate that FedDM algorithms maintain high generation quality across image resolutions. At the same time, the use of quantized updates and proximal terms in the local training objective significantly enhances communication efficiency (up to 4x) and model convergence, particularly in non-IID data settings, at the cost of increased FID scores (up to 1.75x).
Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor
Southwestern University of Finance and Economics（西南财经大学）；University of Electronic Science and Technology of China（电子科技大学）；WeBank（微众银行）；Southwest Jiaotong University（西南交通大学）；Hong Kong University of Science and Technology（香港科技大学）
FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia（新南威尔士大学计算机与信息科技学院）；School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia（悉尼大学电子与计算机工程学院）；QLD Alliance for Agriculture and Food Innovation, The University of Queensland, Brisbane, Australia（昆士兰大学昆士兰农业与食品创新联盟）
Federated learning enables multiple institutions to collaboratively train machine learning models on their local data in a privacy-preserving way. However, its distributed nature often leads to significant heterogeneity in data distributions across institutions. In this paper, we investigate the deleterious impact of a taxonomy of data heterogeneity regimes on federated learning methods, including quantity skew, label distribution skew, and imaging acquisition skew. We show that the performance degrades with the increasing degrees of data heterogeneity. We present several mitigation strategies…
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…
Federated Causal Discovery from Heterogeneous Data
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California San Diego（加利福尼亚大学圣迭戈分校）
Recent advances in wearable devices and Internet-of-Things (IoT) have led to massive growth in sensor data generated in edge devices. Labeling such massive data for classification tasks has proven to be challenging. In addition, data generated by different users bear various personal attributes and edge heterogeneity, rendering it impractical to develop a global model that adapts well to all users. Concerns over data privacy and communication costs also prohibit centralized data accumulation and training. We propose SemiPFL that supports edge users having no label or limited labeled datasets a…
Federated learning is a distributed machine learning paradigm where multiple data owners (clients) collaboratively train one machine learning model while keeping data on their own devices. The heterogeneity of client datasets is one of the most important challenges of federated learning algorithms. Studies have found performance reduction with standard federated algorithms, such as FedAvg, on non-IID data. Many existing works on handling non-IID data adopt the same aggregation framework as FedAvg and focus on improving model updates either on the server side or on clients. In this work, we tac…
FLASH: Federated Learning Across Simultaneous Heterogeneities
University of California, Riverside（加州大学河滨分校）；Brookhaven National Laboratory（布鲁克海文国家实验室）；DEVCOM Army Research Laboratory（国防部陆军研究实验室）；University of Michigan（密歇根大学）
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）
Federated Continual Learning: Concepts, Challenges, and Solutions
Faculty of Computer Science, University of New Brunswick（新 Brunswick大学计算机科学学院）；Department of Electrical and Computer Engineering, University of Windsor（温莎大学电气与计算机工程系）
Enhancing Federated Survival Analysis through Peer-Driven Client Reputation in Healthcare
Department of Computer Science, Missouri University of Science and Technology（计算机科学系，密苏里科学与技术大学）；Department of Mathematical Sciences, University of Alabama in Huntsville（数学科学系，阿拉巴马大学亨茨维尔分校）
FedSKC: Federated Learning with Non-IID Data via Structural Knowledge Collaboration
School of Computing and Information Technology, University of Wollongong, Wollongong, Australia（1 计算与信息科技学院，沃林根大学，澳大利亚）；School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia（2 电气与计算机工程学院，悉尼大学，澳大利亚）；School of Cyber Engineering, Xidian University, Xi’an, China（3 网络工程学院，西安电子科技大学，中国）；QLD Alliance for Agriculture and Food, The University of Queensland, Brisbane, Australia（4 女王艾丽丝州农业与食品联盟，昆士兰大学，澳大利亚）；Principal Research Scientist, CSIRO Data61, Eveleigh, Australia（5 主要研究员，CSIRO Data61，澳大利亚）
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise
Academy for Engineering and Technology, Fudan University（复旦大学工程学院）；School of Computer Science, China University of Geosciences（中国地质大学（武汉）计算机学院）；College of Science, Beijing Forestry University（北京林业大学理学院）
Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning
State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China（虚拟现实技术与系统国家重点实验室，计算机科学与工程学院，北京航空航天大学，北京，中国）；Zhongguancun Laboratory, Beijing, China（中关村实验室，北京，中国）；Center for AI Business Innovation, Department of Management Science and Systems, School of Management, University at Buffalo, USA（人工智能商业创新中心，管理科学与系统系，管理学院，布法罗大学，美国）
Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections
National Center for Tumor Diseases (NCT)（国家肿瘤中心）；Translational Surgical Oncology（转化外科肿瘤学）；Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology（医学系和图林根大学技术大学卡尔·古斯塔夫·卡尔医院）；DKFZ, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology（德累斯顿大学技术大学医学系和德累斯顿癌症研究中心）；Helmholtz-Zentrum Dresden-Rossendorf (HZDR)（德累斯顿-罗斯多夫亥姆霍兹中心）；Centre for Tactile Internet with Human-in-the-Loop (CeTI), TU Dresden（具有人类在环的触觉互联网中心，德累斯顿技术大学）；Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TU Dresden（visceral、胸外科和血管外科，医学系和图林根大学技术大学卡尔·古斯塔夫·卡尔医院）；Weldon School of Biomedical Engineering, Purdue University（生物医学工程韦尔登学校，普渡大学）；Medical Oncology, NCT, University Hospital Heidelberg, Germany（医学肿瘤学，国家肿瘤中心，海德堡大学医院，德国）；Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TU Dresden（医学I，医学系和图林根大学技术大学卡尔·古斯塔夫·卡尔医院）
FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios
Shenzhen University（深圳大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）
Federated learning (FL) involves multiple distributed devices jointly training a shared model without any of the participants having to reveal their local data to a centralized server. Most of previous FL approaches assume that data on devices are fixed and stationary during the training process. However, this assumption is unrealistic because these devices usually have varying sampling rates and different system configurations. In addition, the underlying distribution of the device data can change dynamically over time, which is known as concept drift. Concept drift makes the learning process…
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume. However, solving federated machine learning problems raises issues above and beyond those of centralized machine learning. These issues include setting up communication infrastructure between parties, coordinating the learning process, integrating party results, understanding the characteristics of the training data sets of different participating parties, handling data heterogeneity, and operating with the absence of a…
Federated Incomplete Multi-View Clustering with Heterogeneous Graph Neural Networks
Guangdong University of Foreign Studies（广东外语外贸大学）；School of Engineering, Westlake University（西湖大学工程学院）；East China University of Science and Technology（华东理工大学）
RLOMM: An Efficient and Robust Online Map Matching Framework with Reinforcement Learning
Beijing University of Posts and Telecommunications（北京邮电大学）；Beiyou Shenzhen Institute（北邮深圳研究院）；Nanyang Technological University（南洋理工大学）；Zhejiang University（浙江大学）
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）
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…
