Back to Search
Start Over
Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks
- Source :
- Nikoloska, I & Simeone, O 2022, ' Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks ', IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS . https://doi.org/10.1109/TWC.2022.3195352
- Publication Year :
- 2023
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2023.
-
Abstract
- In this paper, we consider the problem of power control for a wireless network with an arbitrarily time-varying topology, including the possible addition or removal of nodes. A data-driven design methodology that leverages graph neural networks (GNNs) is adopted in order to efficiently parametrize the power control policy mapping the channel state information (CSI) to transmit powers. The specific GNN architecture, known as random edge GNN (REGNN), defines a non-linear graph convolutional filter whose spatial weights are tied to the channel coefficients. While prior work assumed a joint training approach whereby the REGNN-based policy is shared across all topologies, this paper targets adaptation of the power control policy based on limited CSI data regarding the current topology. To this end, we propose a novel modular meta-learning technique that enables the efficient optimization of module assignment. While black-box meta-learning optimizes a general-purpose adaptation procedure via (stochastic) gradient descent, modular meta-learning finds a set of reusable modules that can form components of a solution for any new network topology. Numerical results validate the benefits of meta-learning for power control problems over joint training schemes, and demonstrate the advantages of modular meta-learning when data availability is extremely limited.<br />Comment: Submitted for publication
- Subjects :
- Optimization
Networking and Internet Architecture (cs.NI)
FOS: Computer and information sciences
Computer Science - Machine Learning
Network topology
Computer Science - Information Theory
Information Theory (cs.IT)
Applied Mathematics
Topology
Power control
Resource Allocation
Machine Learning (cs.LG)
Computer Science Applications
Computer Science - Networking and Internet Architecture
Meta-learning
Task analysis
Training
Graph Neural Networks
Electrical and Electronic Engineering
Interference
Subjects
Details
- ISSN :
- 15582248 and 15361276
- Volume :
- 22
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Wireless Communications
- Accession number :
- edsair.doi.dedup.....23b692cb3ce45577bd0a953d47bae9db