Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning

2025/09/30 by Hashmi, Hassaan, Pougkakiotis, Spyridon, Kalogerias, Dionysis
#FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2509.26311

Abstract

We consider the problem of maximizing weighted sum rate in a multiple-input single-output (MISO) downlink wireless network with emphasis on user rate reliability. We introduce a novel risk-aggregated formulation of the complex WSR maximization problem, which utilizes the Conditional Value-at-Risk (CVaR) as a functional for enforcing rate (ultra)-reliability over channel fading uncertainty/risk. We establish a WMMSE-like equivalence between the proposed precoding problem and a weighted risk-averse MSE problem, enabling us to design a tailored unfolded graph neural network (GNN) policy function approximation (PFA), named α-Robust Graph Neural Network (αRGNN), trained to maximize lower-tail (CVaR) rates resulting from adverse wireless channel realizations (e.g., deep fading, attenuation). We empirically demonstrate that a trained αRGNN fully eliminates per user deep rate fades, and substantially and optimally reduces statistical user rate variability while retaining adequate ergodic performance.

Citations

• Distributionally Robust Power Policies for Wireless Systems under Power Fluctuation Risk
• Inexact subgradient methods for semialgebraic functions
• HPE Transformer: Learning to Optimize Multi-Group Multicast Beamforming Under Nonconvex QoS Constraints
• On Outage-based Beamforming Design for Dual-Functional Radar-Communication 6G Systems
• Model-Based Deep Learning
• Stochastic subgradient method converges on tame functions
• Fractional Programming for Communication Systems—Part I: Power Control and Beamforming
• Ultra-Reliable and Low-Latency Wireless Communication: Tail, Risk and Scale
• Ultrareliable and Low-Latency Wireless Communication: Tail, Risk, and Scale
• Robust Transmission for Massive MIMO Downlink with Imperfect CSI
• An Iteratively Weighted MMSE Approach to Distributed Sum-Utility Maximization for a MIMO Interfering Broadcast Channel
• The Graph Neural Network Model

Related

• A Data and Model-Driven Deep Learning Approach to Robust Downlink Beamforming Optimization
• Interference-Limited Ultra-Reliable and Low-Latency Communications: Graph Neural Networks or Stochastic Geometry?
• Graph Neural Networks for Resource Allocation in Interference-limited Multi-Channel Wireless Networks with QoS Constraints
• Centralized & Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization
• GNN-Based Beamforming for Sum-Rate Maximization in MU-MISO Networks