Top Research Papers on Federated Learning

This work proposes a general reinforcement learning-based backdoor attack framework where the attacker first trains a (non-myopic) attack policy using a simulator built upon its local data and common knowledge on the FL system, which is then applied during actual FL training.

A background and comparison of centralized learning, distributed on-site learning, and FL, which is then followed by a survey of the application of FL to cybersecurity for IoT, so readers can have a more thorough understanding of FL for cybersecurity as well as cybersecurity for FL, different security attacks, and countermeasures.

This paper provides the first comprehensive survey of existing federated evaluation methods and explores various applications of federated evaluated methods for enhancing FL performance and presents future research directions by envisioning some challenges.

Federated Reconstruction is introduced, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale and an open-source library is released for evaluating approaches in this setting.

An algorithm called IncFL is proposed that explicitly maximizes the fraction of clients who are incentivized to use the global model by dynamically adjusting the aggregation weights assigned to their updates, and can also improve the generalization performance of theglobal model on unseen clients.

A comprehensive survey of the unique security vulnerabilities exposed by the FL ecosystem is provided, highlighting the vulnerabilities sources, key attacks on FL, defenses, as well as their unique challenges, and discussing promising future research directions towards more robust FL.

MOON is a simple and effective federated learning framework that utilizes the similarity between model representations to correct the local training of individual parties, i.e., conducting contrastive learning in model-level.

This survey explores the domain of personalized FL (PFL) to address the fundamental challenges of FL on heterogeneous data, a universal characteristic inherent in all real-world datasets.

A novel federated learning model that can protect data privacy from the gradient leakage attack and black-box membership inference attack and can successfully defend diverse external attacks to user-level privacy with negligible accuracy loss is proposed.

Two Anarchic Federated Averaging (AFA) algorithms with two-sided learning rates for both cross-device and cross-silo settings are proposed, which achieve the best known convergence rate as the state-of-the-art algorithms for conventional FL.

Key concepts in federated learning and analytics are introduced with an emphasis on how privacy technologies may be combined in real-world systems and how their use charts a path toward societal benefit from aggregate statistics in new domains and with minimized risk to individuals and to the organizations who are custodians of the data.

Building privacy-preserving systems for machine learning and data science on decentralized data.

This survey paper identifies the significance of this emerging research topic of multimodal federated learning (MFL), identifies the feasible application tasks and related benchmarks for MFL and presents a literature review on the state-of-art MFL methods.

This survey provides an introduction to the fundamental concepts and categories of FL, highlights the limitations of the centralized healthcare model, and discusses how FL can address these constraints.

This position paper presents a preliminary comparative analysis of 14 different Federated Learning frameworks, assessing their individual strengths and weaknesses and advocates for a more methodical understanding and selection of FL frameworks, which it believes will substantially benefit both practical applications and future advancements in the field.

A horizontal-based federated learning architecture, empowered by fog federations, devised for the mobile environment is proposed and results show that the proposed model can achieve better accuracy and quality of service than other models presented in the literature.

A relaxed contrastive learning loss is introduced that imposes a divergence penalty on excessively similar sample pairs within each class, which prevents collapsed representations and enhances feature transferability, facilitating collaborative training and leading to significant performance improvements.

A novel Global-Local Forgetting Compensation (GLFC) model is developed, to learn a global class-incremental model for alleviating the catastrophic forgetting from both local and global perspectives, and a prototype gradient-based communication mechanism is developed to protect the privacy.

The concept of Green FL is proposed, which involves optimizing FL parameters and making design choices to minimize carbon emissions consistent with competitive performance and training time, and a data-driven approach to quantify the carbon emissions of FL by directly measuring real-world at-scale FL tasks running on millions of phones is adopted.

This work proposes FedOMD – an online FL algorithm where, akin to the offline setting, clients perform multiple local processing steps before uploading their model predictions to the server, and proves sublinear regret bounds that match their centralized counterparts (up to constants) for both convex and strongly convex losses.

Now the authors are in an era of technology transformation in their everyday life, where data play a key role in the decision making and bringing the action into reality.

A communication-efficient FL framework is proposed to jointly improve the FL convergence time and the training loss, and a probabilistic device selection scheme is designed such that the devices that can significantly improve the convergence speed and training loss have higher probabilities of being selected for ML model transmission.

This work introduces a novel federated learning setting (AFCL) where the continual learning of multiple tasks happens at each client with different orderings and in asynchronous time slots.

We present PeFLL, a new personalized federated learning algorithm that improves over the state-of-the-art in three aspects: 1) it produces more accurate models, especially in the low-data regime, and not only for clients present during its training phase, but also for any that may emerge in the future; 2) it reduces the amount of on-client computation and client-server communication by providing future clients with ready-to-use personalized models that require no additional finetuning or optimization; 3) it comes with theoretical guarantees that establish generalization from the observed clien...

This chapter delves into the core privacy concerns within FL, including the risks of data reconstruction, model inversion attacks, and membership inference, and explores various privacy-preserving techniques, such as Differential Privacy (DP) and Secure Multi-Party Computation (SMPC), which are designed to mitigate these risks.

An unsupervised federated feature selection approach (named FSHFL) for HFL in IoT networks that can select better-federated feature sets among HFL participants, thus improving the performance of the HFL system.

A novel defense mechanism, CrowdGuard, is presented that effectively mitigates backdoor attacks in FL and overcomes the deficiencies of existing techniques and leverages clients' feedback on individual models, analyzes the behavior of neurons in hidden layers, and eliminates poisoned models through an iterative pruning scheme.

This paper forms fairness-controlled federated learning as a dynamical multi-objective optimization problem to ensure the fairness and convergence with theoretical guarantee, and proposes Adaptive Federated Adam (AdaFedAdam) to accelerate fair federated learning with alleviated bias.

While FL appears to be a promising Machine Learning technique to keep the local data private, it is also vulnerable to attacks like other ML models.

This survey comprehensively summarizes and reviews existing decentralized FL approaches proposed in the literature, and identifies emerging challenges and suggests promising research directions in this under-explored domain.

A taxonomy of recent attacks on federated learning systems is provided and the need for more robust threat modeling in Federated learning environments is detailed.

This paper aims at designing an initial model based on which an arbitrary group of clients can obtain a high-accuracy global model for its own purpose, within only a few rounds of FL.

This work proposes FCCL (Federated CrossCorrelation and Continual Learning), which leverages unlabeled public data for communication and construct cross-correlation matrix to learn a generalizable representation under domain shift for heterogeneity problem and catastrophic forgetting.

This project proposes to apply active learning (AL) to the FL framework to reduce the annotation workload, and empirically demonstrates that the F-AL outperforms baseline methods in image classification tasks.

A new algorithm named FL with soft clustering (FLSC) is proposed by combining the strengths ofsoft clustering and IFCA, where the clients are partitioned into overlapping clusters and the information of each participating client is used by multiple clusters simultaneously during each round.

This paper proposes a practical federated learning framework that leverages intermittent energy arrivals for training, with provable convergence guarantees, and can be applied to a wide range of machine learning settings in networked environments, including distributed and Federated learning in wireless and edge networks.

This study proposes Meta Federated Learning (Meta-FL), a novel variant of federated learning which not only is compatible with secure aggregation protocol but also facilitates defense against backdoor attacks.

This survey comprehensively investigates the domain of heterogeneous FL in terms of data space, statistical, system, and model heterogeneity and proposes a precise taxonomy of heterogeneity FL settings for each type of heterogeneity according to the problem setting and learning objective.

A novel federated few-shot learning framework with two separately updated models and dedicated training strategies to reduce the adverse impact of global data variance and local data insufficiency is proposed.

This paper discusses the convergence of key metaverse technologies and FL in detail, such as big data, communication technology, the Internet of Things, edge computing, blockchain, and extended reality, and discusses some key challenges and promising directions of FL4M in detail.

This paper proposes an efficient adaptive algorithm based on the momentum-based variance reduced technique in cross-silo FL and proves that this algorithm is the first adaptive FL algorithm to reach the best-known samples and communication rounds to find an epsilon-stationary point without large batches.

A unique IFL taxonomy is proposed which covers relevant works enabling FL models to explain the prediction results, support model debugging, and provide insights into the contributions made by individual data owners or data samples, which in turn is crucial for allocating rewards fairly to motivate active and reliable participation in FL.

The distributed federated learning scheme demonstrated almost the same level of trained model accuracies and yet significantly faster distributed training, and demonstrates a promising future research direction for scaling and privacy aspects.

This work proposes a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round, using a dynamic regularizer for each device at each round.

This work proposes the federated fair averaging (FedFV) algorithm to mitigate potential conflicts among clients before averaging their gradients, and shows the theoretical foundation of FedFV to mitigate the issue conflicting gradients and converge to Pareto stationary solutions.

The proposed FedDetect learning framework improves the performance by utilizing a local adaptive optimizer and a cross-round learning rate scheduler, and the system efficiency analysis indicates that both end-to-end training time and memory cost are affordable and promising for resource-constrained IoT devices.

It is shown that ModFL outperforms FedPer for non-IID data partitions of CIFAR-10 and STL-10 using CNNs, and argues that the chosen datasets do not highlight the advantages of ModFL, but in the worst case scenario it performs as well as FedPer.

A UAV-enabled covert federated learning architecture, where the UAV is not only responsible for orchestrating the operation of FL but also for emitting artificial noise to interfere with the eavesdropping of unintended users is conceived.

This paper proposes a novel structured federated learning (SFL) framework to learn both the global and personalized models simultaneously using client-wise relation graphs and clients' private data and casts SFL with graph into a novel optimization problem that can model the Client-wise complex relations and graph-based structural topology by a unified framework.

A critical overview of BFL is presented, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of B FL from both Bayesian and federated perspectives.