Federated learning (FL) has prevailed as an efficient and privacy-preserved scheme for distributed learning. In this work, we mainly focus on the optimization of computation and communication in FL from a view of pruning. By adopting layer-wise pruning in local training and federated updating, we formulate an explicit FL pruning framework, FedLP (Federated Layer-wise Pruning), which is model-agnostic and universal for different types of deep learning models. Two specific schemes of FedLP are designed for scenarios with homogeneous local models and heterogeneous ones. Both theoretical and experimental evaluations are developed to verify that FedLP relieves the system bottlenecks of communication and computation with marginal performance decay. To the best of our knowledge, FedLP is the first framework that formally introduces the layer-wise pruning into FL. Within the scope of federated learning, more variants and combinations can be further designed based on FedLP.
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
National University of Singapore（新加坡国立大学）；Northeastern University（东北大学）；University of Technology Sydney（悉尼科技大学）；Tsinghua University（清华大学）；ETH Zurich（苏黎世联邦理工学院）
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective decentralized technique by collaboratively learning a shared prediction model while keeping the data local on different clients devices. However, the limited computation and communication resources on clients devices present practical difficulties for large models. To overcome such challenges, we propose Federated Pruning to train a reduced model under the federated set…
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…
Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data
Hithink RoyalFlush Information Network Co., Ltd.（同花顺网络信息股份有限公司）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Collaborative Innovation Center of Novel Software Technology and Industrialization（新型软件技术与产业化协同创新中心）；Baidu Research（百度研究院）；Software Institute, Peking University（北京大学软件学院）；Auburn University（奥本大学）；North Carolina State University（北卡罗来纳州立大学）；School of Computer Science, Fudan University（复旦大学计算机科学学院）
FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification
Media IC and System Lab, the Graduate Institute of Electronics Engineering and Department of Electrical Engineering, National Taiwan University（媒体IC与系统实验室，电子工程研究所及电气工程系，国立台湾大学）
The prevalent communication efficient federated learning (FL) frameworks usually take advantages of model gradient compression or model distillation. However, the unbalanced local data distributions (either in quantity or quality) of participating clients, contributing non-equivalently to the global model training, still pose a big challenge to these works. In this paper, we propose FedCliP, a novel communication efficient FL framework that allows faster model training, by adaptively learning which clients should remain active for further model training and pruning those who should be inactive…
Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology China（中国科学技术大学）；University of Cambridge（剑桥大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Federated learning alleviates the privacy risk in distributed learning by transmitting only the local model updates to the central server. However, it faces challenges including statistical heterogeneity of clients' datasets and resource constraints of client devices, which severely impact the training performance and user experience. Prior works have tackled these challenges by combining personalization with model compression schemes including quantization and pruning. However, the pruning is data-dependent and thus must be done on the client side which requires considerable computation cost.…
Hong Kong Polytechnic University（香港理工大学）；Dalian University of Technology（大连理工大学）
We explore the problem of selectively forgetting categories from trained CNN classification models in the federated learning (FL). Given that the data used for training cannot be accessed globally in FL, our insights probe deep into the internal influence of each channel. Through the visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we propose a method for scrubbing the model clean of information about particular categories. The method does not require …
Beijing University of Posts and Telecommunications（北京邮电大学）
In this letter, we study a wireless federated learning (FL) system where network pruning is applied to local users with limited resources. Although pruning is beneficial to reduce FL latency, it also deteriorates learning performance due to the information loss. Thus, a trade-off problem between communication and learning is raised. To address this challenge, we quantify the effects of network pruning and packet error on the learning performance by deriving the convergence rate of FL with a non-convex loss function. Then, closed-form solutions for pruning control and bandwidth allocation are p…
Lightweight Federated Learning over Wireless Edge Networks
Department of Electronic Engineering, Tsinghua University（电子工程系，清华大学）；School of Cyber Science and Technology, Beihang University（信息科学与技术学院，北航）；Tsinghua Space Center, Tsinghua University（清华大学空间中心）；College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
School of Computing, Macquarie University（麦考瑞大学计算学院）；School of Information and Physical Sciences, University of Newcastle（纽卡斯尔大学信息与物理科学学院）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；College of Computer Science and Technology, China University of Petroleum (East China)（中国石油大学（华东）计算机科学与技术学院）
Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
Tsinghua University（清华大学）；JD Explore Academy（京东探索研究院）；Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Science and Technology（南京理工大学）；Shenzhen Wisdom and Strategy Technology Co., Ltd.（深圳智略科技有限公司）
Cross-device Federated Learning is an increasingly popular machine learning setting to train a model by leveraging a large population of client devices with high privacy and security guarantees. However, communication efficiency remains a major bottleneck when scaling federated learning to production environments, particularly due to bandwidth constraints during uplink communication. In this paper, we formalize and address the problem of compressing client-to-server model updates under the Secure Aggregation primitive, a core component of Federated Learning pipelines that allows the server to …
Artificial neural network has achieved unprecedented success in the medical domain. This success depends on the availability of massive and representative datasets. However, data collection is often prevented by privacy concerns and people want to take control over their sensitive information during both training and using processes. To address this problem, we propose a privacy-preserving method for the distributed system, Stochastic Channel-Based Federated Learning (SCBF), which enables the participants to train a high-performance model cooperatively without sharing their inputs. Specificall…
Pennsylvania State University（宾夕法尼亚州立大学）；North Carolina State University（北卡罗来纳州立大学）
Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for the task, but a small subset of data with backdoor patterns may trigger the model to make a wrong prediction. There has been an arms race between attackers who tried to conceal attacks and defenders who tried to detect attacks during the aggregation stage of training on the server-side. In this work, we propose a new and effective method to mitigate backdoor attacks after the tr…
ShanghaiTech University（上海科技大学）；LG Electronics（乐金电子）；The University of Hong Kong（香港大学）
Federated learning (FL) is a popular framework for training an AI model using distributed mobile data in a wireless network. It features data parallelism by distributing the learning task to multiple edge devices while attempting to preserve their local-data privacy. One main challenge confronting practical FL is that resource constrained devices struggle with the computation intensive task of updating of a deep-neural network model. To tackle the challenge, in this paper, a federated dropout (FedDrop) scheme is proposed building on the classic dropout scheme for random model pruning. Specific…
FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling
Beijing Key Laboratory of MEMS Technology and Device Reliability for Industrial Internet, the School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（北京工业互联网MEMS技术与器件可靠性重点实验室，智能工程与自动化学院，北京邮电大学）；School of Business Administration, Southwestern University of Finance and Economics（西南财经大学商学院）；Institute of Artificial Intelligence and the School of Computer Science, Beihang University（北京航空航天大学人工智能研究院和计算机学院）；School of Electronic Engineering, Dublin City University（都柏林城市大学电子工程学院）；DreamSoul
Pennsylvania State University（宾夕法尼亚州立大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Purdue University（普渡大学）；Georgia State University（佐治亚州立大学）
Federated learning (FL) enables multiple clients to train models collaboratively without sharing local data, which has achieved promising results in different areas, including the Internet of Things (IoT). However, end IoT devices do not have abilities to automatically annotate their collected data, which leads to the label shortage issue at the client side. To collaboratively train an FL model, we can only use a small number of labeled data stored on the server. This is a new yet practical scenario in federated learning, i.e., labels-at-server semi-supervised federated learning (SemiFL). Alth…
Federated Learning (FL) enables multiple parties to distributively train a ML model without revealing their private datasets. However, it assumes trust in the centralized aggregator which stores and aggregates model updates. This makes it prone to gradient tampering and privacy leakage by a malicious aggregator. Malicious parties can also introduce backdoors into the joint model by poisoning the training data or model gradients. To address these issues, we present BEAS, the first blockchain-based framework for N-party FL that provides strict privacy guarantees of training data using gradient p…
Personalized Federated Learning for Generative AI-Assisted Semantic Communications
School of Intelligent Software and Engineering, Nanjing University（南京大学智能软件与工程学院）；School of Information Science and Engineering, Hunan Normal University（湖南师范大学信息科学与工程学院）；Changsha Social Laboratory of Artificial Intelligence, Hunan University of Technology and Business（湖南工商大学长沙人工智能社会实验室）；Brunel University London（布鲁内尔伦敦大学）
Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eavesdropping attacker can effectively recover image data from gradients transmitted during federated learning. However, little progress has been made in recovering text data. In this paper, we present a novel attack method FILM for federated learning of language models (LMs). For the first time, we show the feasibility of recovering text from large batch sizes of up to 128 sentences. Unlike image-recovery methods that ar…
