analiza aiqbench
This research applies diffusion models combined with graph neural networks to solve constrained resource optimization in wireless networks featuring complex interference patterns. By treating power allocations as stochastic signals, the approach amortizes iterative expert policies into direct sampling methods that achieve near-optimal utility across diverse network states. The work demonstrates strong generalization capabilities for machine learning-driven signal processing tasks within telecommunications infrastructure.
Graph Signal Diffusion Models for Wireless Resource Allocation
arXiv:2604.05175v2 Announce Type: replace-cross Abstract: We consider constrained ergodic resource optimization in wireless networks with graph-structured interference. We train a diffusion model policy to match expert conditional distributions over resource allocations. By leveraging a primal-dual (expert) algorithm, we generate primal iterates that serve as draws from the corresponding expert conditionals for each training network instance. We view the allocations as stochastic graph signals supported on known channel state graphs. We implement the diffusion model architecture as a U-Net hierarchy of graph neural network (GNN) blocks, conditioned on the channel states and additional node states. At inference, the learned generative model amortizes the iterative expert policy by directly sampling allocation vectors from the near-optimal conditional distributions. In a power-control case study, we show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates, with strong generalization and transferability across network states.
Abstract:We consider constrained ergodic resource optimization in wireless networks with graph-structured interference. We train a diffusion model policy to match expert conditional distributions over resource allocations. By leveraging a primal-dual (expert) algorithm, we generate primal iterates that serve as draws from the corresponding expert conditionals for each training network instance. We view the allocations as stochastic graph signals supported on known channel state graphs. We implement the diffusion model architecture as a U-Net hierarchy of graph neural network (GNN) blocks, conditioned on the channel states and additional node states. At inference, the learned generative model amortizes the iterative expert policy by directly sampling allocation vectors from the near-optimal conditional distributions. In a power-control case study, we show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates, with strong generalization and transferability across network states.
Signal Processing (eess.SP); Information Theory (cs.IT); Machine Learning (cs.LG)
arXiv:2604.05175 [eess.SP]
(or arXiv:2604.05175v2 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2604.05175 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 238 cuvinte
Subiecte conexe
NVIDIA AI Releases Dynamo Snapshot: A CRIU-Based Fast Startup System for AI Inference on Kubernetes
MarkTechPost · 5 iun. 2026
Fast State-Augmented Learning for Wireless Resource Allocation with Dual Variable Regression
arXiv · 27 iul. 2026
Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs
arXiv · 3 iun. 2026
The world's best gradual disempowerment model organism: Frontier AI labs
LessWrong · 29 sept. 2026