Unsupervised Learning for Asynchronous Resource Allocation in Ad-hoc Wireless Networks
This addresses resource allocation problems for ad-hoc wireless networks, but it appears incremental as it builds on existing GNN methods with specific adaptations for asynchrony.
The paper tackles optimal resource allocation in asynchronous wireless networks by designing an unsupervised learning method based on Aggregation Graph Neural Networks (Agg-GNNs), which is learned globally and implemented locally, and verifies it through numerical simulations against baseline methods.
We consider optimal resource allocation problems under asynchronous wireless network setting. Without explicit model knowledge, we design an unsupervised learning method based on Aggregation Graph Neural Networks (Agg-GNNs). Depending on the localized aggregated information structure on each network node, the method can be learned globally and asynchronously while implemented locally. We capture the asynchrony by modeling the activation pattern as a characteristic of each node and train a policy-based resource allocation method. We also propose a permutation invariance property which indicates the transferability of the trained Agg-GNN. We finally verify our strategy by numerical simulations compared with baseline methods.