GFlowNets for Active Learning Based Resource Allocation in Next Generation Wireless Networks
This addresses resource allocation in next-generation wireless networks, offering a domain-specific improvement for network optimization.
The paper tackles the radio resource allocation problem in wireless systems with integrated functionalities by proposing a novel active learning framework that uses generative flow networks (GFlowNets) to sample diverse and high-return resource management designs, achieving 20% performance gains and requiring less than half the acquisition rounds compared to benchmarks.
In this work, we consider the radio resource allocation problem in a wireless system with various integrated functionalities, such as communication, sensing and computing. We design suitable resource management techniques that can simultaneously cater to those heterogeneous requirements, and scale appropriately with the high-dimensional and discrete nature of the problem. We propose a novel active learning framework where resource allocation patterns are drawn sequentially, evaluated in the environment, and then used to iteratively update a surrogate model of the environment. Our method leverages a generative flow network (GFlowNet) to sample favorable solutions, as such models are trained to generate compositional objects proportionally to their training reward, hence providing an appropriate coverage of its modes. As such, GFlowNet generates diverse and high return resource management designs that update the surrogate model and swiftly discover suitable solutions. We provide simulation results showing that our method can allocate radio resources achieving 20% performance gains against benchmarks, while requiring less than half of the number of acquisition rounds.