Over-the-Air Federated Learning via Second-Order Optimization

Analyzing massive amounts of data using complex machine learning models requires significant computational resources. The conventional approach to such problems involves centralizing training data and inference processes in the cloud, i.e., in data centers. However, with the proliferation of mobile devices and increasing application of the Internet-of-Things (IoT) paradigm, very large amounts of data are collected at the edges of wireless networks, and due to privacy constraints and limited communication resources, it is undesirable or impractical to upload this data from mobile devices to the cloud for centralized learning. This problem can be solved by distributed learning at the network edge, by which edge devices collaboratively train a shared learning model using real-time mobile data. The avoidance of raw-data uploading not only helps to preserve privacy but may also alleviate network-traffic congestion and minimize latency. With that said, distributed training still requires a substantial amount of information exchange between devices and edge servers over wireless links. In the process, wireless impairments such as noise, interference, and imperfect knowledge of channel states can significantly slow down distributed learning (e.g., convergence speed) and degrades its performance (e.g., learning accuracy). This makes it crucial to optimize wireless network performance so as to support the efficient deployment of distributed learning algorithms. On the other hand, distributed learning algorithms provide a powerful tool-set for solving complex problems in wireless communication and networking. One important framework, called federated learning (FL), enables users to collaboratively learn a shared model while helping to preserve local data privacy. The application of FL can endow edge devices with capabilities of user behavior prediction, user identification, and wireless environment analysis. As another example, distributed reinforcement learning is capable of leveraging distributed computation power and data to solve complex optimization and control problems that arise in various use cases, such as network control, user clustering, resource management, and interference alignment. To cover this paradigm of distributed learning over wireless networks, this two-part Special Issue features papers dealing with two main research challenges: a) optimization of wireless network performance for efficient implementation of distributed learning in wireless networks, and b) distributed learning for solving communication problems and optimizing network performance.

In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL training loss and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that can select the users who can contribute toward improving the FL convergence speed more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time and the FL training loss. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on the global FL model with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission at each given learning step, which enables the BS to improve the global model, the FL convergence speed, and the training loss. Simulation results show that the proposed approach can reduce the FL convergence time by up to 56% and improve the accuracy of identifying handwritten digits by up to 3%, compared to a standard FL algorithm.

In this paper, we consider communication-efficient over-the-air federated learning (FL), where multiple edge devices with non-independent and identically distributed datasets perform multiple local iterations in each communication round and then concurrently transmit their updated gradients to an edge server over the same radio channel for global model aggregation using over-the-air computation (AirComp). We derive the upper bound of the time-average norm of the gradients to characterize the convergence of AirComp-assisted FL, which reveals the impact of the model aggregation errors accumulated over all communication rounds on convergence. Based on the convergence analysis, we formulate an optimization problem to minimize the upper bound to enhance the learning performance, followed by proposing an alternating optimization algorithm to facilitate the transceiver design for AirComp-assisted FL. As the alternating optimization algorithm suffers from high computation complexity, we further develop a knowledge-guided learning algorithm that exploits the structure of the analytic expression of the transmit power to achieve computation-efficient transceiver design. Simulation results demonstrate that the proposed knowledge-guided learning algorithm achieves a comparable performance as the alternating optimization algorithm, but with a much lower computation complexity. Moreover, both proposed algorithms outperform the baseline methods in terms of convergence speed and test accuracy.

With advances in the edge computing (EC) and federated learning (FL) technologies in jointcloud, the edge FL service market has emerged recently and it requires trading edge resources between model requesters and data owners to complete FL tasks, which needs to incentivize sufficient data owners to participate in model training tasks. However, the limitations of resource trading and incentive design for edge FL service market have not been well addressed. In this paper, we propose a two-level blockchain-aided resource trading mechanism for encouraging appropriate edge servers to compete for dynamic FL tasks from the market while incentivizing data owners to participate in the FL tasks. At the upper level, we apply the deep learning-based reverse auction to model the dynamics of the task server selection process, with the aim of maximizing the total social welfare of the edge FL service market, where the edge server, as a seller, considers not only the data contribution of edge devices but also the cost of using blockchain when bidding. At the lower level, the edge servers offer rewards in exchange for the data owners’ participation, while the parameter aggregation is completed through the blockchain in a decentralized manner, which improves the FL’s robustness. Then, we utilize the Stackelberg game to model the dynamic process that the data owners compete for the servers’ revenue. We conduct extensive simulation experiments and the experimental results show that the proposed mechanism is able to get maximized social welfare and provide effective insights and strategies for the resource trading in the edge FL market to complete the federated training.

Edge servers and mobile devices are often assigned a large number of computing tasks. However, the data involved in computing tasks is often sensitive in terms of privacy. Our initial proposal is a federated edge learning strategy based on real-world scenarios, which combines blurred data or pseudo shared data. Federated learning is used to train device models with the aim of protecting privacy while enabling mobile devices to more effectively utilize data for decision-making. In the case of limited energy on mobile devices, we propose a federated edge learning algorithm with blurred data sharing. This algorithm can generate more accurate models by uploading partially blurred data. In order to further improve model accuracy and protect privacy of mobile devices, we propose a federated edge learning algorithm with pseudo data sharing based on dataset distillation and generative adversarial networks (GANs) in scenarios with relatively sufficient energy. The experimental results on several traditional datasets show that our proposed algorithms outperform traditional algorithms in terms of accuracy and energy consumption.

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed; and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×.

Federated learning (FL) is recognized as a key enabling technology to provide intelligent services for future wireless networks and industrial systems with delay and privacy guarantees. However, the performance of wireless FL can be significantly degraded by Byzantine attack, such as data poisoning attack, model poisoning attack and free-riding attack. To design the Byzantine-resilient FL paradigm in wireless networks with limited radio resources, we propose a novel communication-efficient robust model aggregation scheme via over-the-air computation (AirComp). This is achieved by applying the Weiszfeld algorithm to obtain the smoothed geometric median aggregation against Byzantine attack. The additive structure of the Weiszfeld algorithm is further leveraged to match the signal superposition property of multiple-access channels via AirComp, thereby expediting the communication-efficient secure aggregation process of FL. Numerical results demonstrate the robustness against Byzantine devices and good learning performance of the proposed approach.

Federated learning (FL) over wireless networks has become a key enabler for privacy-preserving distributed artificial intelligence (AI). However, high learning latency remains a critical bottleneck due to the presence of stragglers, limited wireless resources, and frequent model uploads. While model quantization can mitigate this issue by reducing communication overhead, its effectiveness is sensitive to device heterogeneity and time-varying channel conditions. To address this issue, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedDamQu</i>, a communication-efficient FL framework with doubly-adaptive model quantization, which dynamically adjusts quantization bit-widths across devices and communication rounds to balance latency and accuracy. Our objective is to maximize the model performance under learning latency constraints. The main contributions are summarized as follows. 1) Convergence Analysis under Unreliable Channels: We derive a novel convergence error upper bound for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedDamQu</i>, which explicitly quantifies the impact of device selection, unreliable transmission, and quantization error on the global model performance, under both fixed and dynamic quantization gain settings. 2) Joint Optimization Framework: Based on the knowledge from the proposed theoretical bound, we formulate a joint mixed integer nonlinear programming (MINLP) problem that integrates device selection, quantization bit-width configuration, and bandwidth allocation to minimize the convergence error under latency constraints. 3) Efficient Solution Design: The MINLP problem is decomposed into three subproblems, where closed-form solutions for quantization bit-width configuration and bandwidth allocation subproblems are derived, and a lightweight yet effective iterative algorithm is developed to obtain a suboptimal solution for the device selection subproblem. Extensive experiment results validate the theoretical analysis and demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedDamQu</i> consistently outperforms existing methods in terms of convergence rate and model accuracy, while significantly reducing the overall learning latency.

In order to meet the extremely heterogeneous requirements of the next generation wireless communication networks, research community is increasingly dependent on using machine‐learning solutions for real‐time decision‐making and radio resource management. Traditional machine learning employs fully centralized architecture in which the entire training data is collected at one node for example, cloud server, that significantly increases the communication overheads and also raises severe privacy concerns. Toward this end, a distributed machine‐learning paradigm termed as federated learning (FL) has been proposed recently. In FL, each participating edge device trains its local model by using its own training data. Then, via the wireless channels the weights or parameters of the locally trained models are sent to the central parameter server (PS), that aggregates them and updates the global model. On one hand, FL plays an important role for optimizing the resources of wireless communication networks, on the other hand, wireless communications is crucial for FL. Thus, a “bidirectional” relationship exists between FL and wireless communications. Although FL is an emerging concept, many publications have already been published in the domain of FL and its applications for next generation wireless networks. Nevertheless, we noticed that none of the works have highlighted the bidirectional relationship between FL and wireless communications. Therefore, the purpose of this survey article is to bridge this gap in literature by providing a timely and comprehensive discussion on the interdependency between FL and wireless communications.

This paper studies a federated learning (FL) system, where <i>multiple</i> FL services co-exist in a wireless network and share common wireless resources. It fills the void of wireless resource allocation for multiple simultaneous FL services in the existing literature. Our method designs a two-level resource allocation framework comprising <i>intra-service</i> resource allocation and <i>inter-service</i> resource allocation. The intra-service resource allocation problem aims to minimize the length of FL rounds by optimizing the bandwidth allocation among the clients of each FL service. Based on this, an inter-service resource allocation problem is further considered, which distributes bandwidth resources among multiple simultaneous FL services. We consider both cooperative and selfish providers of the FL services. For cooperative FL service providers, we design a distributed bandwidth allocation algorithm to optimize the overall performance of multiple FL services, meanwhile catering it to the fairness among FL services and the privacy of clients. For selfish FL service providers, a new auction scheme is designed with the FL service providers as the bidders and the network operator as the auctioneer. The designed auction scheme strikes a balance between the overall FL performance and fairness. Our simulation results show that the proposed algorithms outperform other benchmarks under various network conditions.

Mobile edge computing aims to deploy mobile applications at the edge of wireless networks. Federated learning in mobile edge computing is a forward-looking distributed framework for deploying deep learning algorithms in many application scenarios. One challenge of federated learning in mobile edge computing is data heterogeneity since the unified model of federated learning performs poorly when client data are non-independent and identically distributed. Personalized federated learning can obtain amazing models in scenarios where client data are non-independent and identically distributed. This is because the personalized model captures the features of users’ local data more accurately than the unified model. The personalized federated learning problem under two-tier (server-client) federated learning structures has been widely studied and applied. However, a lot of research results exhibit three distinct limitations: 1) suboptimal communication efficiency, 2) slow model convergence, and 3) underutilization of the relationships within user data, resulting in lower accuracy of personalized models. In this paper, we present the first personalized federated learning algorithm based on the client-edge-cloud structure. The edge server is responsible for model personalization and employs a learnable mixing parameter to mix the local model and the global model. We also utilize two learnable normalization parameters trained by clients to improve the performance of personalized models. Furthermore, in order to facilitate the collaboration among edge servers, we propose a similarity aggregation method to assign aggregation weights based on the Tanimoto coefficients between models. The experimental results show that the proposed algorithm not only increases the convergence speed of personalized models but also improves their testing accuracy.

Federated learning (FL) has been considered as a promising distributed learning tool in massive data mining for different local devices. Addressing in the trust risk of centralized model aggregation and the challenge of data heterogeneity in traditional FL, this paper proposes an enhancement FL approach in a blockchain network. By analyzing the shortcakes of the classic FL that is widely used in the blockchain enabled FL networks, we propose a novel local parameter update approach, where the information of the last-round global model is utilized to reduce the local performance drift caused by data heterogeneity. The convergence of the proposed FL approach is then proved and the convergence rate is revealed to be linear to the training time. Finally, extensive experiments are carried out with a public dataset to validate the effectiveness of the proposed approach with comparisons of two classic baseline approaches.

In this study, we propose an over-the-air computation (OAC) scheme to calculate the majority vote (MV) for federated edge learning (FEEL). With the proposed approach, edge devices (EDs) transmit the signs of local stochastic gradients, i.e., votes, by activating one of two orthogonal resources. The MVs at the edge server (ES) are obtained with non-coherent detectors by exploiting the accumulations on the resources. Hence, the proposed scheme eliminates the need for channel state information (CSI) at the EDs and ES. In this study, we analyze various gradient-encoding strategies through the weight functions and waveform configurations over orthogonal frequency division multiplexing (OFDM). We show that specific weight functions that enable absentee EDs (i.e., hard-coded participation with absentees (HPA)) or weighted votes (i.e., soft-coded participation (SP)) can substantially reduce the probability of detecting the incorrect MV. By taking path loss, power control, cell size, and fading channel into account, we prove the convergence of the distributed learning for a non-convex function for HPA. Through simulations, we show that the proposed scheme with HPA and SP can provide high test accuracy even when the time-synchronization and the power control are not ideal under heterogeneous data distribution scenarios.

Motivated by the ever-increasing demands for massive data processing and intelligent data analysis at the network edge, federated learning (FL), a distributed architecture for machine learning, has been introduced to enhance edge intelligence without compromising data privacy. Nonetheless, due to the large number of edge devices (referred to as clients in FL) with only limited wireless resources, client scheduling, which chooses only a subset of devices to participate in each round of FL, becomes a more feasible option. Unfortunately, the training latency can be intolerable in the iterative process of FL. To tackle the challenge, this article introduces update-importance-based client scheduling schemes to reduce the required number of rounds. Then latency-based client scheduling schemes are proposed to shorten the time interval for each round. We consider the scenario where no prior information regarding the channel state and the resource usage of the devices is available, and propose a scheme based on the multi-armed bandit theory to strike a balance between exploration and exploitation. Finally, we propose a latency-based technique that exploits update importance to reduce the training time. Computer simulation results are presented to evaluate the convergence rate with respect to the rounds and wall-clock time consumption.

In cellular federated edge learning (FEEL), multiple edge devices holding local data jointly train a neural network by communicating learning updates with an access point without exchanging their data samples. With very limited communication resources, it is beneficial to schedule the most informative local learning updates. This paper focuses on FEEL with gradient averaging over participating devices in each round of communication. A novel scheduling policy is proposed to exploit both diversity in multiuser channels and diversity in the “importance” of the edge devices' learning updates. First, a new probabilistic scheduling framework is developed to yield unbiased update aggregation in FEEL. The importance of a local learning update is measured by its gradient divergence. If one edge device is scheduled in each communication round, the scheduling policy is derived in closed form to achieve the optimal trade-off between channel quality and update importance. The probabilistic scheduling framework is then extended to allow scheduling multiple edge devices in each communication round. Numerical results obtained using popular models and learning datasets demonstrate that the proposed scheduling policy can achieve faster model convergence and higher learning accuracy than conventional scheduling policies that only exploit a single type of diversity.