Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Advances and Open Problems in Federated Learning

Federated learning has been a hot research topic in enabling the collaborative training of machine learning models among different organizations under the privacy restrictions. As researchers try to support more machine learning models with different privacy-preserving approaches, there is a requirement in developing systems and infrastructures to ease the development of various federated learning algorithms. Similar to deep learning systems such as PyTorch and TensorFlow that boost the development of deep learning, federated learning systems (FLSs) are equivalently important, and face challenges from various aspects such as effectiveness, efficiency, and privacy. In this survey, we conduct a comprehensive review on federated learning systems. To achieve smooth flow and guide future research, we introduce the definition of federated learning systems and analyze the system components. Moreover, we provide a thorough categorization for federated learning systems according to six different aspects, including data distribution, machine learning model, privacy mechanism, communication architecture, scale of federation and motivation of federation. The categorization can help the design of federated learning systems as shown in our case studies. By systematically summarizing the existing federated learning systems, we present the design factors, case studies, and future research opportunities.

A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection

Federated learning enables multiple parties to collaboratively train a machine learning model without communicating their local data. A key challenge in federated learning is to handle the heterogeneity of local data distribution across parties. Although many studies have been proposed to address this challenge, we find that they fail to achieve high performance in image datasets with deep learning models. In this paper, we propose MOON: model-contrastive federated learning. MOON is a simple and effective federated learning framework. The key idea of MOON is to utilize the similarity between model representations to correct the local training of individual parties, i.e., conducting contrastive learning in model-level. Our extensive experiments show that MOON significantly outperforms the other state-of-the-art federated learning algorithms on various image classification tasks.

/pdf/model-contrastive-federated-learning-bm9nbbwnna.pdf

Model-Contrastive Federated Learning

Federated learning (FL) is a rapidly growing research field in machine learning. However, existing FL libraries cannot adequately support diverse algorithmic development; inconsistent dataset and model usage make fair algorithm comparison challenging. In this work, we introduce FedML, an open research library and benchmark to facilitate FL algorithm development and fair performance comparison. FedML supports three computing paradigms: on-device training for edge devices, distributed computing, and single-machine simulation. FedML also promotes diverse algorithmic research with flexible and generic API design and comprehensive reference baseline implementations (optimizer, models, and datasets). We hope FedML could provide an efficient and reproducible means for developing and evaluating FL algorithms that would benefit the FL research community. We maintain the source code, documents, and user community at this https URL.

FedML: A Research Library and Benchmark for Federated Machine Learning

The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learning solutions assume the existence of (cloud-based) central entities that are in charge of processing the data. Nonetheless, the difficulty of accessing private data, together with the high cost of transmitting raw data to the central entity gave rise to a decentralized machine learning approach called Federated Learning . The main idea of federated learning is to perform an on-device collaborative training of a single machine learning model without having to share the raw training data with any third-party entity. Although few survey articles on federated learning already exist in the literature, the motivation of this survey stems from three essential observations. The first one is the lack of a fine-grained multi-level classification of the federated learning literature, where the existing surveys base their classification on only one criterion or aspect. The second observation is that the existing surveys focus only on some common challenges, but disregard other essential aspects such as reliable client selection, resource management and training service pricing. The third observation is the lack of explicit and straightforward directives for researchers to help them design future federated learning solutions that overcome the state-of-the-art research gaps. To address these points, we first provide a comprehensive tutorial on federated learning and its associated concepts, technologies and learning approaches. We then survey and highlight the applications and future directions of federated learning in the domain of communication and networking. Thereafter, we design a three-level classification scheme that first categorizes the federated learning literature based on the high-level challenge that they tackle. Then, we classify each high-level challenge into a set of specific low-level challenges to foster a better understanding of the topic. Finally, we provide, within each low-level challenge, a fine-grained classification based on the technique used to address this particular challenge. For each category of high-level challenges, we provide a set of desirable criteria and future research directions that are aimed to help the research community design innovative and efficient future solutions. To the best of our knowledge, our survey is the most comprehensive in terms of challenges and techniques it covers and the most fine-grained in terms of the multi-level classification scheme it presents.

/pdf/federated-machine-learning-survey-multi-level-classification-qdw5jveh7p.pdf

Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems

Federated learning is a distributed framework for training machine learning models over the data residing at mobile devices, while protecting the privacy of individual users. A major bottleneck in scaling federated learning to a large number of users is the overhead of secure model aggregation across many users. In particular, the overhead of the state-of-the-art protocols for secure model aggregation grows quadratically with the number of users. In this article, we propose the first secure aggregation framework, named Turbo-Aggregate, that in a network with $N$ users achieves a secure aggregation overhead of $O(N\log {N})$ , as opposed to $O(N^{2})$ , while tolerating up to a user dropout rate of 50%. Turbo-Aggregate employs a multi-group circular strategy for efficient model aggregation, and leverages additive secret sharing and novel coding techniques for injecting aggregation redundancy in order to handle user dropouts while guaranteeing user privacy. We experimentally demonstrate that Turbo-Aggregate achieves a total running time that grows almost linear in the number of users, and provides up to $40\times $ speedup over the state-of-the-art protocols with up to $N=200$ users. Our experiments also demonstrate the impact of model size and bandwidth on the performance of Turbo-Aggregate.

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Secure federated learning is a privacy-preserving framework to improve machine learning models by training over large volumes of data collected by mobile users. This is achieved through an iterative process where, at each iteration, users update a global model using their local datasets. Each user then masks its local update via random keys, and the masked models are aggregated at a central server to compute the global model for the next iteration. As the local updates are protected by random masks, the server cannot observe their true values. This presents a major challenge for the resilience of the model against adversarial (Byzantine) users, who can manipulate the global model by modifying their local updates or datasets. Towards addressing this challenge, this paper presents the first single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning. BREA is based on an integrated stochastic quantization, verifiable outlier detection, and secure model aggregation approach to guarantee Byzantine-resilience, privacy, and convergence simultaneously. We provide theoretical convergence and privacy guarantees and characterize the fundamental trade-offs in terms of the network size, user dropouts, and privacy protection. Our experiments demonstrate convergence in the presence of Byzantine users, and comparable accuracy to conventional federated learning benchmarks.

Byzantine-Resilient Secure Federated Learning

/pdf/codedprivateml-a-fast-and-privacy-preserving-framework-for-1pgmrdz32c.pdf

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning.

How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML’s privacy threshold and prove its convergence for logistic (and linear) regression. Furthermore, via extensive experiments on Amazon EC2, we demonstrate that CodedPrivateML provides significant speedup over cryptographic approaches based on multi-party computing (MPC).

Jinhyun So

Papers

FedML: A Research Library and Benchmark for Federated Machine Learning

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning

Byzantine-Resilient Secure Federated Learning

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning.

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning