Scalable Hybrid Architecture for Wireless Collaborative Federated Learning (SHAFT)
Lead Research Organisation:
Queen Mary University of London
Department Name: Sch of Electronic Eng & Computer Science
Abstract
Unlike previous generations of mobile networks, the beyond 5G (B5G) network is envisioned to support edge intelligence, which is to provide both communication and computing capabilities to the proximity of end users. Wireless edge intelligence is particularly important to those crucial use cases of B5G, including smart cities, autonomous driving, wireless healthcare, virtual reality (VR) and augmented reality (AR) gaming, where mobile networks are expected to be equipped with intelligent capabilities for prediction and shaping experiences to individuals. Federated learning (FL) is a key enabling technology for wireless edge intelligence, by performing the model training in a decentralized manner and keeping the data where it is generated. However, a straightforward adaption of FL from computer networks to wireless systems can suffer performance degradation in spectral and implementation efficiency, because of the complex wireless environment with heterogeneous resources and a massive number of devices. The aim of this project is to develop a novel scalable hybrid architecture for wireless FL by efficiently utilising the physical layer dynamics of the mobile communication environments and exploiting sophisticated service-aware and resource-aware collaborative edge learning. The novelty of the project is the development of this novel edge learning architecture, where the fundamental limits of the learning architecture is characterised by advanced mathematical tools, such as graph theory and stochastic learning. In addition, an algorithmic framework for quantifying challenging design trade-offs in the presence of practical constraints by applying sophisticated tools such as compressed sensing and machine learning.
Publications
Chen Z
(2024)
Robust Federated Learning for Unreliable and Resource-Limited Wireless Networks
in IEEE Transactions on Wireless Communications
Chen Z
(2024)
Adaptive Model Pruning for Communication and Computation Efficient Wireless Federated Learning
in IEEE Transactions on Wireless Communications
Chen Z
(2024)
Efficient Wireless Federated Learning With Partial Model Aggregation
in IEEE Transactions on Communications
Chen Z
(2023)
Knowledge-Aided Federated Learning for Energy-Limited Wireless Networks
in IEEE Transactions on Communications
Chen Z
(2024)
Distributed Digital Twin Migration in Multi-Tier Computing Systems
in IEEE Journal of Selected Topics in Signal Processing
Chen Z
(2024)
Adaptive Semi-Asynchronous Federated Learning over Wireless Networks
in IEEE Transactions on Communications
Chen Z
(2024)
Exploring Representativity in Device Scheduling for Wireless Federated Learning
in IEEE Transactions on Wireless Communications
Fayaz M
(2024)
Toward Autonomous Power Control in Semi-Grant-Free NOMA Systems: A Power Pool-Based Approach
in IEEE Transactions on Communications
Liu M
(2024)
A Nonorthogonal Uplink/Downlink IoT Solution for Next-Generation ISAC Systems
in IEEE Internet of Things Journal
Masaracchia A
(2025)
The Role of Digital Twin in 6G-based URLLCs: Current Contributions, Research Challenges, and Next Directions
in IEEE Open Journal of the Communications Society
| Description | Platform Driving The Ultimate Connectivity |
| Amount | £2,030,861 (GBP) |
| Funding ID | EP/X04047X/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 04/2023 |
| End | 04/2026 |
| Description | TITAN Extension |
| Amount | £10,612,161 (GBP) |
| Funding ID | EP/Y037243/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 01/2024 |
| End | 03/2025 |
| Description | Collaborative Research on Federated Learning |
| Organisation | University of Cambridge |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Proposed two mini projects for the TITAN Extension EPSRC Project (EP/Y037243/1), lead by University of Cambridge. |
| Collaborator Contribution | Two newly proposed mini projects are 1. AI-aided Pareto Optimization for UAV Swarm Trajectory Planning in NTNs Problem statement and brief state-of-the art summary (include an illustration if possible): multi-objective optimization (MOO) plays a pivotal role in the realm of airport flight planning, and its relevance extends to the domain of UAV Swarm Trajectory Planning in NTNs. In addition to conventional objectives, e.g., communication quality, energy consumption, and collision avoidance, UAV swarm introduces a new optimisation domain, i.e., swarm structures. During the planning phase, it is important to acknowledge the full potential of the considered system. The Pareto front (PF) becomes a pivotal indicator, with each point along this front representing an optimal solution. At the execution stage, we can choose the desired solution based on changeable constraints. Traditional MOO solution transforms the problem into a weighted single-objective optimisation problem, which only achieves one point on the PF. Some recent works use deep deterministic policy gradient (DDPG) algorithm to optimize this MOO problem, but the swarm structure optimisation and Pareto front are not included. Proposed new approach and methodology, provide a list of tasks and milestones: The first task is to design UAV swarm structures, where multi-agent reinforcement learning (MA-RL) can be developed to dynamically control the swarm by interacting with the environment. Based on the proposed swarm solution, the second task is to propose the PF via MO-soft actor and critic (SAC) algorithms. Milestones: 1) Design MA-RL algorithms for optimising UAV swarm structures; 2) Design MO-SAC algorithms for obtaining PF of the successful data packet rate and energy consumption under the fixed UAV swarm structure; and 3) Design multi-phase MO-SAC algorithms for obtaining PF for hybrid (centric + distributed) UAV swarm structure. 2. Federated Multi-modal Learning for Sensing and Communications Problem statement and brief state-of-the art summary (include an illustration if possible): Sensor fusion via wireless channels is important for sensing and communication systems as radiofrequency (RF) sensing has relatively low range resolution. However, different sensor belongs to different companies. The sensor fusion needs to consider both the multi-modal and privacy-protection problems. Existing works uses auto-encoder and federated average algorithms to solve this issue, but the auto-encoder structure design needs to manually access the local dataset on different agent and the federated average algorithm costs huge communication resources. Proposed new approach and methodology, provide a list of tasks and milestones: This project will first design a semi-supervised auto-encoder via variational Autoencoders to avoid leaking users' privacy. Then, this project will integrate the proposed auto-encoder algorithm into a new federated learning structure, where communication load via wireless channels will be minimized by considering the pruning and partial model transmitting. Milestones: 1) Semi-supervised auto-encoder algorithm for abstracting the common feature of multi-modal datasets; and 2) Federated multi-modal learning algorithm for the improve the performance of sensing and communications. |
| Impact | This collaboration started very recently. Research outcomes yet to come. |
| Start Year | 2023 |