Over-the-Air Federated Graph Learning
- 8 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (12) , 18669-18683
Abstract
Message-passing graph neural network (MPGNN) shows tremendous promise in modeling complex networks by capturing the interaction among vertices via the messaging-passing mechanism. However, the dimension of MPGNN is tied to the size of vertices in the graph, which varies from graph to graph, resulting in dimension mismatch that hinders the utilization of graph data distributed at the network edge. To address this issue, we in this paper leverage the attention mechanism to project the graph representation of MPGNNs into a unified space and apply over-the-air computation (AirComp) to support federated graph learning (FGL) over wireless networks. By explicitly deriving the upper bound on the convergence of over-the-air FGL, we formulate a long-term transmission distortion minimization problem, which is further decomposed into a series of online optimization problems by using Lyapunov optimization. We further propose a deep reinforcement learning based algorithm to optimize the AirComp transceiver, where the analytical expression of transmit power is exploited in the action design to reduce the searching space and also enhance the training performance. Simulations demonstrate that, compared to the benchmarks, the proposed algorithm attains two orders of magnitude acceleration in the inference stage, while exhibiting enhanced robustness and improving learning performance.Keywords
Funding Information
- Natural Science Foundation of Shanghai Municipality (23ZR1442800)
- National Natural Science Foundation of China (U20A20159)
- National Natural Science Foundation of China (62271318)
This publication has 38 references indexed in Scilit:
- Machine Learning for Large-Scale Optimization in 6G Wireless NetworksIEEE Communications Surveys & Tutorials, 2023
- ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding2023
- Trustworthy Federated Learning via BlockchainIEEE Internet of Things Journal, 2022
- Group-Free 3D Object Detection via Transformers2021
- Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking SystemsIEEE Communications Surveys & Tutorials, 2021
- Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical AnalysisIEEE Journal on Selected Areas in Communications, 2020
- Message Passing Neural Networks2020
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge ComputingProceedings of the IEEE, 2019
- Dynamic Computation Offloading for Mobile-Edge Computing With Energy Harvesting DevicesIEEE Journal on Selected Areas in Communications, 2016