Journal article
Hybrid-Task Meta-Learning: A GNN Approach for Scalable and Transferable Bandwidth Allocation
IEEE Transactions on Wireless Communications, Vol.23(12), pp.19820-19835
2024
Abstract
In this paper, we develop a deep learning-based bandwidth allocation policy that is: 1) scalable with the number of users and 2) transferable to different communication scenarios, such as non-stationary wireless channels, different quality-of-service (QoS) requirements, and dynamically available resources. To support scalability, the bandwidth allocation policy is represented by a graph neural network (GNN), with which the number of training parameters does not change with the number of users. To enable the generalization of the GNN, we develop a hybrid-task meta-learning (HML) algorithm that trains the initial parameters of the GNN with different communication scenarios during meta-training. Next, during meta-testing, a few samples are used to fine-tune the GNN with unseen communication scenarios. Simulation results demonstrate that our HML approach can improve the initial performance by 8.79%, and sample efficiency by 73%, compared with existing benchmarks. After fine-tuning, our near-optimal GNN-based policy can achieve close to the same reward with much lower inference complexity compared to the optimal policy obtained using iterative optimization. Numerical results validate that our HML can reduce the computation time by approximately 200 to 2000 times than the optimal iterative algorithm.
Details
- Title
- Hybrid-Task Meta-Learning: A GNN Approach for Scalable and Transferable Bandwidth Allocation
- Authors
- Xin Hao - Deakin UniversityChangyang She - Harbin Institute of TechnologyPhee Lep Yeoh - University of the Sunshine Coast, Queensland, School of Science, Technology and EngineeringYuhong Liu - University of SydneyBranka Vucetic - University of SydneyYonghui Li - University of Sydney
- Publication details
- IEEE Transactions on Wireless Communications, Vol.23(12), pp.19820-19835
- Publisher
- Institute of Electrical and Electronics Engineers
- Date published
- 2024
- DOI
- 10.1109/TWC.2024.3487533
- ISSN
- 1558-2248
- Organisation Unit
- School of Science, Technology and Engineering
- Language
- English
- Record Identifier
- 991083398402621
- Output Type
- Journal article
Metrics
7 Record Views