The increasing complexity of deep neural networks poses significant barriers to democratizing AI to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution that enables device-server co-training through model splitting. However, although system optimization substantially influences the performance of SFL, the problem remains largely uncharted. In this paper, we first provide a unified convergence analysis of SFL, which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on its learning performance, laying a theoretical foundation for this field. Based on this convergence bound, we introduce AdaptSFL, an adaptive SFL framework to accelerate SFL under resource-constrained edge computing systems. Specifically, AdaptSFL adaptively controls MS and client-side MA to balance communication-computing latency and training convergence. Extensive simulations across various datasets validate that our proposed AdaptSFL framework takes considerably less time to achieve target accuracy than existing benchmarks.
29 April 2025 in IEEE Transactions on Mobile Computing
As AI models expand in size, it has become increasingly challenging to deploy federated learning (FL) on resource-constrained edge devices. To tackle this issue, split federated learning (SFL) has emerged as an FL framework with reduced workload on edge devices via model splitting; it has received extensive attention from the research community in recent years. Nevertheless, most prior works on SFL focus only on a two-tier architecture without harnessing multi-tier cloud-edge computing resources. In this paper, we intend to analyze and optimize the learning performance of SFL under multi-tier systems. Specifically, we propose the hierarchical SFL (HSFL) framework and derive its convergence bound. Based on the theoretical results, we formulate a joint optimization problem for model splitting (MS) and model aggregation (MA). To solve this rather hard problem, we then decompose it into MS and MA sub-problems that can be solved via an iterative descending algorithm. Simulation results demonstrate that the tailored algorithm can effectively optimize MS and MA in multi-tier systems and significantly outperform existing schemes.
27 October 2023 in IEEE Transactions on Neural Networks and Learning Systems
To meet requirements for real-time trajectory scheduling and distributed coordination, underwater target hunting task is challenging in terms of turbulent ocean environments and dynamic adversarial environment. Despite the existing research in game-based target hunting area, few approaches have considered dynamic environmental factors, such as sea currents, winds, and communication delay. In this article, we focus on a target hunting system consisted of multiple unmanned underwater vehicles (UUVs) and a target with high maneuverability. Besides, differential game theory is leveraged to analyze adversarial behaviors between hunters and the escapee. However, it is intractable that UUVs have to deploy an adaptive scheme to guarantee the consistency and avoid the escape of the target without collision. Therefore, we conceive the Hamiltonian function with Leibniz’s formula to obtain feedback control policies. In addition, it proves that the target hunting system is asymptotically stable in the mean, and the system can satisfy Nash equilibrium relying on the proposed control policies. Furthermore, we design a modified multiagent reinforcement learning (MARL) to facilitate the underwater target hunting task under the constraints of energetic flows and acoustic propagation delay. Simulation results show that the proposed scheme is superior to the typical MARL algorithm in terms of reward and success rate.
In recent years, the Internet of Underwater Things (IoUT) has garnered significant attention owing to its potential in ocean exploration and monitoring. However, environmental erosion and limited energy can cause node failures, leading to routing voids, communication congestion, and even IoUT breakdowns. Addressing these challenges, this work considers a node repair scheme for multiple autonomous underwater vehicles (AUVs) to search and repair faulty nodes to ensure the stable operation of the IoUT networks. Moreover, AUVs should adapt automatically to the unknown environment, working in cooperative or separative modes to balance repair efficiency and coverage. We propose a multiagent reinforcement learning-based AUV-assisted node repair (RANR) scheme, which considers limited underwater communication and scheduling between AUVs. To further enhance work efficiency, we introduce area information entropy to reduce redundant coverage among AUVs. Simulation results demonstrate that the RANR scheme is highly applicable to different working conditions.
The development of automatic underwater vehicles (AUVs) has brought about unprecedented profits and opportunities. In order to discover the hidden valuable data detected by an AUV swarm, it is necessary to aggregate the data detected by AUV swarm to generate a powerful machine learning model. Traditional centralized machine learning generates a large number of data exchanges and faces problems of enormous training data, large-scale models, and communication. In underwater environments, radio waves are strongly absorbed, and acoustic communication is the only feasible technology. Unlike electromagnetic wave communication on land, the bandwidth of underwater acoustic communication is extremely limited, with the transmission rate being only of the electromagnetic wave. Therefore, traditional centralized machine learning cannot support underwater AUV swarm training. In recent years, federated learning could only interact with model parameters without interacting with data, which greatly reduced communication costs. Therefore, this paper introduces federated learning into the collaboration of an AUV swarm. In order to further reduce the constraints of underwater scarce communication resources on federated learning and alleviate the straggler effect, in this work, we designed an asynchronous federated learning method. Finally, we constructed the optimization problem of minimizing the weighted sum of delay and energy consumption, relying on jointly optimizing the AUV CPU frequency and signal transmission power. In order to solve this complex optimization problem of high-dimensional non-convex time series accumulation, we transformed the problem into a Markov decision process (MDP) and use the proximal policy optimization 2 (PPO2) algorithm to solve this problem. The simulation results demonstrate the effectiveness and superiority of our method.
The complex and time-varying marine environment puts forward demanding requirements for the structural design and algorithm development of unmanned underwater vehicles (UUVs). It is inevitable to repeatedly evaluate the feasibility of autonomy schemes to enhance the intelligence and security of the UUV before putting it into use. Considering the high cost of the UUV hardware platform and the high risk of underwater experiments, this study aims to evaluate and optimize autonomy schemes in the manner of software-in-loop (SIL) simulation efficiently. Therefore, a self-feedback development framework is proposed and a multi-interface, programmable modular simulation platform for UUV based on a robotic operating system (ROS) is designed. The platform integrates the 3D marine environment, UUV models, sensor plugins, motion control plugins in a modular manner, and reserves programming interfaces for users to test various algorithms. Subsequently, we demonstrate the simulation details with cases, such as single UUV path planning, task scheduling, and multi-UUV formation control, and construct underwater experiments to confirm the feasibility of the simulation platform. Finally, the extensibility of the simulation platform and the related performance analysis are discussed.