DNN-Enabled Multi-User Beamforming for Throughput Maximization under Adjustable Fairness
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911452018769920 |
|---|---|
| author | Lu, Kaifeng Rupp, Markus Schwarz, Stefan |
| author_facet | Lu, Kaifeng Rupp, Markus Schwarz, Stefan |
| contents | Ensuring user fairness in wireless communications is a fundamental challenge, as balancing the trade-off between fairness and sum rate leads to a non-convex, multi-objective optimization whose complexity grows with network scale. To alleviate this conflict, we propose an optimization-based unsupervised learning approach based on the wireless transformer (WiT) architecture that learns from channel state information (CSI) features. We reformulate the trade-off by combining the sum rate and fairness objectives through a Lagrangian multiplier, which is updated automatically via a dual-ascent algorithm. This mechanism allows for a controllable fairness constraint while simultaneously maximizing the sum rate, effectively realizing a trace on the Pareto front between two conflicting objectives. Our findings show that the proposed approach offers a flexible solution for managing the trade-off optimization under prescribed fairness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15617 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DNN-Enabled Multi-User Beamforming for Throughput Maximization under Adjustable Fairness Lu, Kaifeng Rupp, Markus Schwarz, Stefan Machine Learning Networking and Internet Architecture Ensuring user fairness in wireless communications is a fundamental challenge, as balancing the trade-off between fairness and sum rate leads to a non-convex, multi-objective optimization whose complexity grows with network scale. To alleviate this conflict, we propose an optimization-based unsupervised learning approach based on the wireless transformer (WiT) architecture that learns from channel state information (CSI) features. We reformulate the trade-off by combining the sum rate and fairness objectives through a Lagrangian multiplier, which is updated automatically via a dual-ascent algorithm. This mechanism allows for a controllable fairness constraint while simultaneously maximizing the sum rate, effectively realizing a trace on the Pareto front between two conflicting objectives. Our findings show that the proposed approach offers a flexible solution for managing the trade-off optimization under prescribed fairness. |
| title | DNN-Enabled Multi-User Beamforming for Throughput Maximization under Adjustable Fairness |
| topic | Machine Learning Networking and Internet Architecture |
| url | https://arxiv.org/abs/2602.15617 |