Federated Learning (FL) methods adopt efficient communication technologies to distribute machine learning tasks across edge devices, reducing the overhead in terms of data storage and computational complexity compared to centralized solutions. Rather than moving large data volumes from producers (sensors, machines) to energy-hungry data centers, raising environmental concerns due to resource demands, FL provides an alternative solution to mitigate the energy demands of several learning tasks while enabling new Artificial Intelligence of Things (AIoT) applications. This paper proposes a framework for real-time monitoring of the energy and carbon footprint impacts of FL systems. The carbon tracking tool is evaluated for consensus (fully decentralized) and classical FL policies. For the first time, we present a quantitative evaluation of different computationally and communication efficient FL methods from the perspectives of energy consumption and carbon equivalent emissions, suggesting also general guidelines for energy-efficient design. Results indicate that consensus-driven FL implementations should be preferred for limiting carbon emissions when the energy efficiency of the communication is low (i.e., < 25 Kbit/Joule). Besides, quantization and sparsification operations are shown to strike a balance between learning performances and energy consumption, leading to sustainable FL designs.
Mobility-Aware Asynchronous Federated Learning with Dynamic Sparsification
Beijing National Research Center for Information Science and Technology, Department of Electronic Engineering, Tsinghua University（北京信息科学与技术国家研究中心，电子工程系，清华大学）；School of Electronic and Information Engineering, Beijing Jiaotong University（电子与信息工程学院，北京交通大学）
Princeton University（普林斯顿大学）；University of Chicago（芝加哥大学）；IBM
Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on targeted sub-tasks (e.g. classifying planes as birds) by uploading "poisoned" updates. In this report we introduce \algoname{}, a novel defense that uses global top-k update sparsification and device-level gradient clipping to mitigate model poisoning attacks. We propose a theoretical framework for analyzing the robustness of defenses against poisoning attacks…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning. Existing methods that ensure user-level DP come at the cost of severe accuracy decrease. In this paper, we study the cause of model performance degradation in federated learning under user-level DP guarantee. We find the key to solving this issue is to naturally restrict the norm of local updates before executing operations that guarantee DP. To this end, we propose two techniques, Bounded Local Update Regularization and Local Update Sparsif…
The University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. However, data locality does not provide sufficient privacy protection, and it is desirable to facilitate FL with rigorous differential privacy (DP) guarantee. Existing DP mechanisms would introduce random noise with magnitude proportional to the model size, which can be quite large in deep neural networks. In this paper, we propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient pert…
Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy
Hong Kong University of Science and Technology（香港科技大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Southern University of Science and Technology（南方科技大学）
Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）；Tsinghua University（清华大学）；Imperial College London（伦敦帝国理工学院）
Federated edge learning (FEEL) is a promising distributed machine learning (ML) framework to drive edge intelligence applications. However, due to the dynamic wireless environments and the resource limitations of edge devices, communication becomes a major bottleneck. In this work, we propose time-correlated sparsification with hybrid aggregation (TCS-H) for communication-efficient FEEL, which exploits jointly the power of model compression and over-the-air computation. By exploiting the temporal correlations among model parameters, we construct a global sparsification mask, which is identical…
Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification
Institute of Communications Engineering, National Tsing Hua University（国立清华大学通信工程研究所）；University of Electronic Science and Technology of China（电子科技大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Yonsei University（延世大学）
Imperial College London（帝国理工学院）；Ozyegin University（奥兹耶金大学）
Federated learning (FL) enables multiple clients to collaboratively train a shared model without disclosing their local datasets. This is achieved by exchanging local model updates with the help of a parameter server (PS). However, due to the increasing size of the trained models, the communication load due to the iterative exchanges between the clients and the PS often becomes a bottleneck in the performance. Sparse communication is often employed to reduce the communication load, where only a small subset of the model updates are communicated from the clients to the PS. In this paper, we int…
China University of Political Science Law（中国政法大学）；Xi’an Jiaotong University（西安交通大学）；Ant Rongxin (Chengdu) Network Technology Co Ltd（蚂蚁融信（成都）网络科技有限公司）
The conventional machine learning (ML) and deep learning approaches need to share customers' sensitive information with an external credit bureau to generate a prediction model that opens the door to privacy leakage. This leakage risk makes financial companies face an enormous challenge in their cooperation. Federated learning is a machine learning setting that can protect data privacy, but the high communication cost is often the bottleneck of the federated systems, especially for large neural networks. Limiting the number and size of communications is necessary for the practical training of …
Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning
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）；School of Cyber Science and Technology at Beihang University（北京航空航天大学网络安全科学与技术学院）；School of Cyberspace Science and Technology, Beijing Jiaotong University（北京交通大学网络空间科学与技术学院）；Beijing Key Laboratory of Security and Privacy in Intelligent Transportation（北京智能交通安全与隐私重点实验室）；Zhongguancun Laboratory（中关村实验室）；School of Computing and Information,University of Pittsburgh（匹兹堡大学计算与信息学院）
Imperial College London（帝国理工学院）；IBM T. J. Watson Research Center（IBM T·J·沃森研究中心）
Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication overhead and improve the overall efficiency of FL, gradient sparsification (GS) can be applied, where instead of the full gradient, only a small subset of important elements of the gradient is communicated. Existing work on GS uses a fixed degree of gradient sparsity for i.i.d.-distributed data within a datacenter. In this paper, we consider adaptive degree of s…
Efficient Asynchronous Federated Learning with Sparsification and Quantization
School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）；Hithink RoyalFlush Information Network Co., Ltd.（同花顺信息服务股份有限公司）；Collaborative Innovation Center of Novel Software Technology and Industrialization（新型软件技术及产业化协同创新中心）；Department of Sciences and Informatics, Muroran Institute of Technology（室兰工业大学科学与信息学系）；Boston Consulting Group（波士顿咨询公司）
Homomorphic encryption (HE) is a promising privacy-preserving technique for cross-silo federated learning (FL), where organizations perform collaborative model training on decentralized data. Despite the strong privacy guarantee, general HE schemes result in significant computation and communication overhead. Prior works employ batch encryption to address this problem, but it is still suboptimal in mitigating communication overhead and is incompatible with sparsification techniques. In this paper, we propose FLASHE, an HE scheme tailored for cross-silo FL. To capture the minimum requirements o…
Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization
Pillar of Information Systems Technology and Design（信息系统技术与设计学院）；School of Information Science and Engineering（信息科学与工程学院）；School of Cyber Science and Engineering（网络安全科学与工程学院）；National Mobile Communications Research Laboratory（国家移动通信研究实验室）；School of Electronic and Optical Engineering（电子与光学工程学院）；School of Electronics, Electrical Engineering and Computer Science (EEECS)（电子、电气工程与计算机科学学院）；Data61, CSIRO（Data61，CSIRO）；Department of Electronics Engineering（电子工程系）；Department of Electrical and Computer Engineering（电气与计算机工程系）
Secure aggregation is a popular protocol in privacy-preserving federated learning, which allows model aggregation without revealing the individual models in the clear. On the other hand, conventional secure aggregation protocols incur a significant communication overhead, which can become a major bottleneck in real-world bandwidth-limited applications. Towards addressing this challenge, in this work we propose a lightweight gradient sparsification framework for secure aggregation, in which the server learns the aggregate of the sparsified local model updates from a large number of users, but w…
Rice University（莱斯大学）；University of Houston-Downtown（休斯顿大学市中心分校）；Prudence Medical Technologies Ltd.（审慎医疗技术有限公司）
The Internet of Things (IoT) revolution has shown potential to give rise to many medical applications with access to large volumes of healthcare data collected by IoT devices. However, the increasing demand for healthcare data privacy and security makes each IoT device an isolated island of data. Further, the limited computation and communication capacity of wearable healthcare devices restrict the application of vanilla federated learning. To this end, we propose an advanced federated learning framework to train deep neural networks, where the network is partitioned and allocated to IoT devic…
Green Federated Learning via Carbon-Aware Client and Time Slot Scheduling
Inria Centre at Université Côte d’Azur（法国国家信息与自动化技术研究院（Inria）亚维农分校）；Accenture（埃森哲）；Department of Electrical Engineering (ISY), Linköping University（利厄普大学电气工程系）
Model compression is important in federated learning (FL) with large models to reduce communication cost. Prior works have been focusing on sparsification based compression that could desparately affect the global model accuracy. In this work, we propose a new scheme for upstream communication where instead of transmitting the model update, each client learns and transmits a light-weight synthetic dataset such that using it as the training data, the model performs similarly well on the real training data. The server will recover the local model update via the synthetic data and apply standard …
Zhejiang University（浙江大学）；Wuhan University（武汉大学）；Singapore University of Technology and Design（新加坡科技设计大学）；North Carolina State University（北卡罗来纳州立大学）
Communication overhead has become one of the major bottlenecks in the distributed training of deep neural networks. To alleviate the concern, various gradient compression methods have been proposed, and sign-based algorithms are of surging interest. However, SIGNSGD fails to converge in the presence of data heterogeneity, which is commonly observed in the emerging federated learning (FL) paradigm. Error feedback has been proposed to address the non-convergence issue. Nonetheless, it requires the workers to locally keep track of the compression errors, which renders it not suitable for FL since…
Modern large scale machine learning applications require stochastic optimization algorithms to be implemented on distributed computational architectures. A key bottleneck is the communication overhead for exchanging information, such as stochastic gradients, among different nodes. Recently, gradient sparsification techniques have been proposed to reduce communications cost and thus alleviate the network overhead. However, most of gradient sparsification techniques consider only synchronous parallelism and cannot be applied in asynchronous scenarios, such as asynchronous distributed training fo…
Federated learning can enable remote workers to collaboratively train a shared machine learning model while allowing training data to be kept locally. In the use case of wireless mobile devices, the communication overhead is a critical bottleneck due to limited power and bandwidth. Prior work has utilized various data compression tools such as quantization and sparsification to reduce the overhead. In this paper, we propose a predictive coding based compression scheme for federated learning. The scheme has shared prediction functions among all devices and allows each worker to transmit a compr…
Northeastern University（东北大学）；Duke University（杜克大学）；University of Connecticut（康涅狄格大学）
Nowadays, Deep Neural Networks are widely applied to various domains. However, massive data collection required for deep neural network reveals the potential privacy issues and also consumes large mounts of communication bandwidth. To address these problems, we propose a privacy-preserving method for the federated learning distributed system, operated on Intel Software Guard Extensions, a set of instructions that increase the security of application code and data. Meanwhile, the encrypted models make the transmission overhead larger. Hence, we reduce the commutation cost by sparsification and …
Imperial College London（帝国理工学院）；Sabanci University（萨班哲大学）
We study collaborative machine learning (ML) across wireless devices, each with its own local dataset. Offloading these datasets to a cloud or an edge server to implement powerful ML solutions is often not feasible due to latency, bandwidth and privacy constraints. Instead, we consider federated edge learning (FEEL), where the devices share local updates on the model parameters rather than their datasets. We consider a heterogeneous cellular network (HCN), where small cell base stations (SBSs) orchestrate FL among the mobile users (MUs) within their cells, and periodically exchange model updat…
Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers, raising environmental concerns due to computational and communication resource demands, while violating privacy. Emerging alternatives to mitigate such high energy costs propose to efficiently distribute, or federate, the learning tasks across devices, which are typically low-power. This paper proposes a novel framework for the analysis of energy and carbon footprints in distributed and federated learning (FL). The proposed framework quantifies bo…
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…
Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；School of Computing, Faculty of Science and Engineering, Macquarie University（麦考瑞大学计算学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University（深圳大学广东省人工智能与数字经济实验室）；Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程学系）；School of Computing Science, Simon Fraser University（西蒙菲莎大学计算科学学院）
University of Cambridge（剑桥大学）；Avignon Université（阿维尼翁大学）；Adap；University College London（伦敦大学学院）
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers. In response, alternatives to centralized training such as Federated Learning (FL) have emerged. Perhaps unexpectedly, FL, in particular, is starting to be deployed at a global scale by companies that must adhere to new legal demands and policies originating from governments and the civil society for privacy protection. However, the potential environmental impact related to FL remains unclear and unexplored. This pap…
Federated Learning for Global Carbon Emission Forecasting: A Hybrid Time-Series Approach with Statistical and Neural Models
School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；Department of Computer Science, Bahria University（巴里亚大学计算机科学系）；School of Mechanical Engineering, Southwest Jiaotong University（西南交通大学机械工程学院）
We provide the optimal receive combining strategy for federated learning in multiple-input multiple-output (MIMO) systems. Our proposed algorithm allows the clients to perform individual gradient sparsification which greatly improves performance in scenarios with heterogeneous (non i.i.d.) training data. The proposed method beats the benchmark by a wide margin.
Distributed learning techniques such as federated learning have enabled multiple workers to train machine learning models together to reduce the overall training time. However, current distributed training algorithms (centralized or decentralized) suffer from the communication bottleneck on multiple low-bandwidth workers (also on the server under the centralized architecture). Although decentralized algorithms generally have lower communication complexity than the centralized counterpart, they still suffer from the communication bottleneck for workers with low network bandwidth. To deal with t…
In this paper, we question the rationale behind propagating large numbers of parameters through a distributed system during federated learning. We start by examining the rank characteristics of the subspace spanned by gradients across epochs (i.e., the gradient-space) in centralized model training, and observe that this gradient-space often consists of a few leading principal components accounting for an overwhelming majority (95-99%) of the explained variance. Motivated by this, we propose the "Look-back Gradient Multiplier" (LBGM) algorithm, which exploits this low-rank property to enable gr…
Consiglio Nazionale delle Ricerche (CNR)（意大利国家研究委员会）；University of Oulu（奥卢大学）
Recent advances in distributed learning raise environmental concerns due to the large energy needed to train and move data to/from data centers. Novel paradigms, such as federated learning (FL), are suitable for decentralized model training across devices or silos that simultaneously act as both data producers and learners. Unlike centralized learning (CL) techniques, relying on big-data fusion and analytics located in energy hungry data centers, in FL scenarios devices collaboratively train their models without sharing their private data. This article breaks down and analyzes the main factors…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）
Communicating information, like gradient vectors, between computing nodes in distributed and federated learning is typically an unavoidable burden, resulting in scalability issues. Indeed, communication might be slow and costly. Recent advances in communication-efficient training algorithms have reduced this bottleneck by using compression techniques, in the form of sparsification, quantization, or low-rank approximation. Since compression is a lossy, or inexact, process, the iteration complexity is typically worsened; but the total communication complexity can improve significantly, possibly …
We investigate the problem of private read update write (PRUW) in federated submodel learning (FSL) with sparsification. In FSL, a machine learning model is divided into multiple submodels, where each user updates only the submodel that is relevant to the user's local data. PRUW is the process of privately performing FSL by reading from and writing to the required submodel without revealing the submodel index, or the values of updates to the databases. Sparsification is a widely used concept in learning, where the users update only a small fraction of parameters to reduce the communication cos…
Federated learning (FL) has recently become a hot research topic, in which Byzantine robustness, communication efficiency and privacy preservation are three important aspects. However, the tension among these three aspects makes it hard to simultaneously take all of them into account. In view of this challenge, we theoretically analyze the conditions that a communication compression method should satisfy to be compatible with existing Byzantine-robust methods and privacy-preserving methods. Motivated by the analysis results, we propose a novel communication compression method called consensus …
Learnable Sparse Customization in Heterogeneous Edge Computing
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 for Network Sciences and Cyberspace, Tsinghua University（清华大学网络科学与网络空间研究院）；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）
Semnan University（塞姆南大学）；Iran University of Science and Technology（伊朗科技大学）；Amirkabir University of Technology（阿米尔卡比尔理工大学）；Boston University（波士顿大学）
Federated Learning marks a turning point in the implementation of decentralized machine learning (especially deep learning) for wireless devices by protecting users' privacy and safeguarding raw data from third-party access. It assigns the learning process independently to each client. First, clients locally train a machine learning model based on local data. Next, clients transfer local updates of model weights and biases (training data) to a server. Then, the server aggregates updates (received from clients) to create a global learning model. However, the continuous transfer between clients …
University of Houston（休斯顿大学）；Xidian University（西安电子科技大学）；University of Florida（佛罗里达大学）
The continuous convergence of machine learning algorithms, 5G and beyond (5G+) wireless communications, and artificial intelligence (AI) hardware implementation hastens the birth of federated learning (FL) over 5G+ mobile devices, which pushes AI functions to mobile devices and initiates a new era of on-device AI applications. Despite the remarkable progress made in FL, huge energy consumption is one of the most significant obstacles restricting the development of FL over battery-constrained 5G+ mobile devices. To address this issue, in this paper, we investigate how to develop energy efficien…
Sichuan University（四川大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Reducing communication overhead in federated learning (FL) is challenging but crucial for large-scale distributed privacy-preserving machine learning. While methods utilizing sparsification or others can largely lower the communication overhead, the convergence rate is also greatly compromised. In this paper, we propose a novel method, named single-step synthetic features compressor (3SFC), to achieve communication-efficient FL by directly constructing a tiny synthetic dataset based on raw gradients. Thus, 3SFC can achieve an extremely low compression rate when the constructed dataset contains…
