Seoul National University（首尔大学）；University of Oulu（奥卢大学）；Deakin University（迪肯大学）；Yonsei University（延世大学）
Hyowoon Seo, Jihong Park, Seungeun Oh, Mehdi Bennis, Seong-Lyun Kim
备注：
30 pages, 12 figures, 2 tables; This chapter is written for the forthcoming book, Machine Learning and Wireless Communications (Cambridge University Press), edited by H. V. Poor, D. Gunduz, A. Goldsmith, and Y. Eldar
Distributed learning frameworks often rely on exchanging model parameters across workers, instead of revealing their raw data. A prime example is federated learning that exchanges the gradients or weights of each neural network model. Under limited communication resources, however, such a method becomes extremely costly particularly for modern deep neural networks having a huge number of model parameters. In this regard, federated distillation (FD) is a compelling distributed learning solution that only exchanges the model outputs whose dimensions are commonly much smaller than the model sizes (e.g., 10 labels in the MNIST dataset). The goal of this chapter is to provide a deep understanding of FD while demonstrating its communication efficiency and applicability to a variety of tasks. To this end, towards demystifying the operational principle of FD, the first part of this chapter provides a novel asymptotic analysis for two foundational algorithms of FD, namely knowledge distillation (KD) and co-distillation (CD), by exploiting the theory of neural tangent kernel (NTK). Next, the second part elaborates on a baseline implementation of FD for a classification task, and illustrates its performance in terms of accuracy and communication efficiency compared to FL. Lastly, to demonstrate the applicability of FD to various distributed learning tasks and environments, the third part presents two selected applications, namely FD over asymmetric uplink-and-downlink wireless channels and FD for reinforcement learning.
Personalization in federated learning (FL) functions as a coordinator for clients with high variance in data or behavior. Ensuring the convergence of these clients' models relies on how closely users collaborate with those with similar patterns or preferences. However, it is generally challenging to quantify similarity under limited knowledge about other users' models given to users in a decentralized network. To cope with this issue, we propose a personalized and fully decentralized FL algorithm, leveraging knowledge distillation techniques to empower each device so as to discern statistical …
Is it possible to design an universal API for federated learning using which an ad-hoc group of data-holders (agents) collaborate with each other and perform federated learning? Such an API would necessarily need to be model-agnostic i.e. make no assumption about the model architecture being used by the agents, and also cannot rely on having representative public data at hand. Knowledge distillation (KD) is the obvious tool of choice to design such protocols. However, surprisingly, we show that most natural KD-based federated learning protocols have poor performance. To investigate this, we pr…
KAIST（韩国科学技术院）；Institute for Basic Science（基础科学研究所）；Microsoft Research Asia（微软亚洲研究院）；Tsinghua University（清华大学）
This paper presents FedX, an unsupervised federated learning framework. Our model learns unbiased representation from decentralized and heterogeneous local data. It employs a two-sided knowledge distillation with contrastive learning as a core component, allowing the federated system to function without requiring clients to share any data features. Furthermore, its adaptable architecture can be used as an add-on module for existing unsupervised algorithms in federated settings. Experiments show that our model improves performance significantly (1.58--5.52pp) on five unsupervised algorithms.
The performance of federated learning in neural networks is generally influenced by the heterogeneity of the data distribution. For a well-performing global model, taking a weighted average of the local models, as done by most existing federated learning algorithms, may not guarantee consistency with local models in the space of neural network maps. In this paper, we propose a novel framework of federated learning equipped with the process of decentralized knowledge distillation (FedDKD) (i.e., without data on the server). The FedDKD introduces a module of decentralized knowledge distillation …
Institute of High Performance Computing, A*STAR（新加坡科技研究局高性能计算研究所）；Vellore Institute of Technology（韦洛尔理工学院）；College of Engineering, Anna University（安娜大学工程学院）；Measi Academy Of Architecture（米西建筑学院）
Federated Deep Learning frameworks can be used strategically to monitor Land Use locally and infer environmental impacts globally. Distributed data from across the world would be needed to build a global model for Land Use classification. The need for a Federated approach in this application domain would be to avoid transfer of data from distributed locations and save network bandwidth to reduce communication cost. We use a Federated UNet model for Semantic Segmentation of satellite and street view images. The novelty of the proposed architecture is the integration of Knowledge Distillation to…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；Sony AI（索尼人工智能研究院）
Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. However, model updates are large in size if the model contains numerous parameters, and there usually needs many rounds of communication until model converges. Thus, the communication cost in federated learning can be quite heavy. In this paper, we propose a communication efficient federated learning method based on knowledge distillation. Instead of directly communicating the large models betwee…
FedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learning
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Federated learning (FL), which utilizes communication between the server (core) and local devices (edges) to indirectly learn from more data, is an emerging field in deep learning research. Recently, Knowledge Distillation-based FL methods with notable performance and high applicability have been suggested. In this paper, we choose knowledge distillation-based FL method as our baseline and tackle a challenging problem that ensues from using these methods. Especially, we focus on the problem incurred in the server model that tries to mimic different datasets, each of which is unique to an indiv…
The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients. The collaborative learning framework by typically aggregating model updates is vulnerable to model poisoning attacks from adversarial clients. Since the shared information between the global server and participants are only limited to model parameters, it is challenging to detect bad model updates. Moreover, real-world datasets are usually heterogeneous and not independent and identically distributed (Non-IID) among participants, which makes …
Peak-Controlled Logits Poisoning Attack in Federated Distillation
School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机与信息技术学院）；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）
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a pr…
Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications（重庆邮电大学通信与信息工程学院）
University at Buffalo（布法罗大学）；United Imaging Intelligence（联影智能）
Federated Learning (FL) is a machine learning paradigm where local nodes collaboratively train a central model while the training data remains decentralized. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they suffer from communication bottlenecks. More importantly, they risk privacy leakage. In this work, we develop a privacy preserving and communication efficient method in a FL framework with one-shot offline knowledge distillation using unlabeled, cross-domain public data. We propose a quantized a…
Federated Learning (FL) is designed to protect the data privacy of each client during the training process by transmitting only models instead of the original data. However, the trained model may memorize certain information about the training data. With the recent legislation on right to be forgotten, it is crucially essential for the FL model to possess the ability to forget what it has learned from each client. We propose a novel federated unlearning method to eliminate a client's contribution by subtracting the accumulated historical updates from the model and leveraging the knowledge dist…
Harvard University（哈佛大学）；Yale University（耶鲁大学）；University of Pennsylvania（宾夕法尼亚大学）
Federated learning enables the creation of a powerful centralized model without compromising data privacy of multiple participants. While successful, it does not incorporate the case where each participant independently designs its own model. Due to intellectual property concerns and heterogeneous nature of tasks and data, this is a widespread requirement in applications of federated learning to areas such as health care and AI as a service. In this work, we use transfer learning and knowledge distillation to develop a universal framework that enables federated learning when each agent owns no…
Huazhong University of Science and Technology（华中科技大学）；Lehigh University（理海大学）；Google Research（谷歌研究院）
Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, due to the heterogeneity of the system and data, many approaches suffer from the "client-drift" issue that could significantly slow down the convergence of the global model training. As clients perform local updates on heterogeneous data through heterogeneous systems, their local models drift apart. To tackle this issue, one intuitive idea is to guide the local model training by the global teachers, i.e., past global m…
FedICT: Federated Multi-task Distillation for Multi-access 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）；Zhongguancun Laboratory（中关村实验室）
Jiangsu University（江苏大学）；Southwest University（西南大学）；The University of Sydney（悉尼大学）；Monash University（莫纳什大学）；Sichuan University（四川大学）；Nanyang Technological University（南洋理工大学）
Pusan National University（釜山国立大学）；University of Technology Sydney（悉尼科技大学）；University of Warwick（华威大学）
In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks; and (2) how to be robust against an environment with heterogeneous data. Realizing the first problem, we aim to design a novel FL framework named Full-stack FL (F2L). More specifically, F2L utilizes a hierarchical network architecture, making extending the FL network accessible without reconstructing the whole network system. Moreover, leveraging the advantages of hierarchical network design, we propose a new label-driven knowledge distillation (LKD) techn…
Towards Personalized Federated Learning via Comprehensive Knowledge 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, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）
Knowledge Distillation in Federated Edge Learning: A Survey
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）
Tsinghua University（清华大学）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
The recent advent of various forms of Federated Knowledge Distillation (FD) paves the way for a new generation of robust and communication-efficient Federated Learning (FL), where mere soft-labels are aggregated, rather than whole gradients of Deep Neural Networks (DNN) as done in previous FL schemes. This security-per-design approach in combination with increasingly performant Internet of Things (IoT) and mobile devices opens up a new realm of possibilities to utilize private data from industries as well as from individuals as input for artificial intelligence model training. Yet in previous …
Xidian University（西安电子科技大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）；Queen’s University（女王大学）
In this paper, to deal with the heterogeneity in federated learning (FL) systems, a knowledge distillation (KD) driven training framework for FL is proposed, where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset. To overcome the challenge of train the big teacher model in resource limited user devices, the digital twin (DT) is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources. Then, during model distillation, each user can update the parameters…
Collaborative Innovation Center of Railway Traffic Safety, Beijing Jiaotong University（北京交通大学轨道交通运行安全协同创新中心）；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）
USTC（中国科学技术大学）；University of Leeds（利兹大学）；Beihang University（北京航空航天大学）；NERC-RPP, CAEIT（中国电子科技集团公司信息科学研究院国家电磁辐射控制工程技术研究中心）；Tsinghua University（清华大学）
Social bot detection is of paramount importance to the resilience and security of online social platforms. The state-of-the-art detection models are siloed and have largely overlooked a variety of data characteristics from multiple cross-lingual platforms. Meanwhile, the heterogeneity of data distribution and model architecture makes it intricate to devise an efficient cross-platform and cross-model detection framework. In this paper, we propose FedACK, a new federated adversarial contrastive knowledge distillation framework for social bot detection. We devise a GAN-based federated knowledge d…
FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems
Faculty of EEE, Phenikaa School of Engineering（电子工程系，Phenikaa工程学院）；Phenikaa University（Phenikaa大学）；VinUni-Illinois Smart Health Center（VinUniversity-伊利诺伊智能健康中心）；VinUniversity（Vin大学）；College of Engineering & Computer Science（工程与计算机科学学院）
Southwest Jiaotong University（西南交通大学）；Chengdu University of Information Technology（成都信息工程大学）；University of Nottingham（诺丁汉大学）
This paper proposes an efficient federated distillation learning system (EFDLS) for multi-task time series classification (TSC). EFDLS consists of a central server and multiple mobile users, where different users may run different TSC tasks. EFDLS has two novel components, namely a feature-based student-teacher (FBST) framework and a distance-based weights matching (DBWM) scheme. Within each user, the FBST framework transfers knowledge from its teacher's hidden layers to its student's hidden layers via knowledge distillation, with the teacher and student having identical network structure. For…
Federated Knowledge Distillation for Multi-Model Architectures Lithography Hotspot Detection
City University of New York（纽约城市大学）；Sichuan Agricultural University（四川农业大学）；The University of Sydney（悉尼大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of St Andrews（圣安德鲁大学）；Southwest University（西南大学）
Partial Knowledge Distillation for Alleviating the Inherent Inter-Class Discrepancy in Federated Learning
College of Informatics Huazhong Agricultural University（华中农业大学信息学院）；Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology（香港科技大学电子与计算机工程系）；NVIDIA Corporation（NVIDIA公司）
DeepFusion: Accelerating MoE Training via Federated Knowledge Distillation from Heterogeneous Edge Devices
School of Electronic Engineering and Computer Science, Queen Mary University of London（伦敦女王玛丽大学电子工程与计算机科学学院）；Department of Computer Science, Faculty of Environment, Science and Economy, University of Exeter（埃克塞特大学环境、科学与经济学院计算机科学系）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Beijing Key Laboratory of Petroleum Data Mining, China University of Petroleum（北京石油数据挖掘重点实验室，中国石油大学）
East China Normal University（华东师范大学）；Zaozhuang University（枣庄学院）；University of Houston（休斯顿大学）；University of Technology Sydney（悉尼科技大学）
As a promising distributed machine learning paradigm, Federated Learning (FL) trains a central model with decentralized data without compromising user privacy, which has made it widely used by Artificial Intelligence Internet of Things (AIoT) applications. However, the traditional FL suffers from model inaccuracy since it trains local models using hard labels of data and ignores useful information of incorrect predictions with small probabilities. Although various solutions try to tackle the bottleneck of the traditional FL, most of them introduce significant communication and memory overhead,…
FedSKD: Aggregation-free Model-heterogeneous Federated Learning via Multi-dimensional Similarity Knowledge Distillation for Medical Image Classification
