Learning to Unfold Fractional Programming for Multi-Cell MU-MIMO Beamforming with Graph Neural Networks
Abstract
In the multi-cell multiuser multi-input multi-output (MU-MIMO) systems, fractional programming (FP) has demonstrated considerable effectiveness in optimizing beamforming vectors, yet it suffers from high computational complexity. Recent improvements demonstrate reduced complexity by avoiding large-dimension matrix inversions (i.e., FastFP) and faster convergence by learning to unfold the FastFP algorithm (i.e., DeepFP).
Fields of Study & Subjects
Advanced MIMO Systems Optimization
Millimeter-Wave Propagation and Modeling
Advanced Wireless Network Optimization
Publication details
- Journal / source
- arXiv (Cornell University)
- Publication date
- 12 January 2026
- Document type
- Preprint