Graph Neural Networks for Resource Allocation in Interference-limited Multi-Channel Wireless Networks with QoS Constraints

• URL: http://arxiv.org/abs/2509.06395v1
• Date: Mon, 08 Sep 2025 07:28:10 GMT
• Title: Graph Neural Networks for Resource Allocation in Interference-limited Multi-Channel Wireless Networks with QoS Constraints
• Authors: Lili Chen, Changyang She, Jingge Zhu, Jamie Evans,
• Abstract summary: Meeting minimum data rate constraints is a significant challenge in wireless communication systems.<n>Traditional deep learning approaches often address these constraints by incorporating penalty terms into the loss function and hyper tuning.<n>We build upon the structure of the WMMSE algorithm and extend it to a multi-channel setting.<n>We develop a GNN-based algorithm, JCPGNN-M, capable of supporting simultaneous multi-channel allocation per user.
• Score: 24.147078012070285
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Meeting minimum data rate constraints is a significant challenge in wireless communication systems, particularly as network complexity grows. Traditional deep learning approaches often address these constraints by incorporating penalty terms into the loss function and tuning hyperparameters empirically. However, this heuristic treatment offers no theoretical convergence guarantees and frequently fails to satisfy QoS requirements in practical scenarios. Building upon the structure of the WMMSE algorithm, we first extend it to a multi-channel setting with QoS constraints, resulting in the enhanced WMMSE (eWMMSE) algorithm, which is provably convergent to a locally optimal solution when the problem is feasible. To further reduce computational complexity and improve scalability, we develop a GNN-based algorithm, JCPGNN-M, capable of supporting simultaneous multi-channel allocation per user. To overcome the limitations of traditional deep learning methods, we propose a principled framework that integrates GNN with a Lagrangian-based primal-dual optimization method. By training the GNN within the Lagrangian framework, we ensure satisfaction of QoS constraints and convergence to a stationary point. Extensive simulations demonstrate that JCPGNN-M matches the performance of eWMMSE while offering significant gains in inference speed, generalization to larger networks, and robustness under imperfect channel state information. This work presents a scalable and theoretically grounded solution for constrained resource allocation in future wireless networks.

Related papers

• Communication-Efficient Quantum Federated Learning over Large-Scale Wireless Networks [21.963665862623245]
  Quantum learning (QFL) combines the robust data processing of computing with the privacy-preserving federated learning (FL)<n>In large-scale wireless networks, optimizing sum-centric, for unlocking the true potential of QFL, is crucial.<n>This paper is specifically designed for non-orthoortho access (NOMA) networks.
  arXiv  Detail & Related papers  (2026-03-01T18:41:15Z)
• Graph Neural Networks for Resource Allocation in Multi-Channel Wireless Networks [15.680699077140453]
  We propose an enhanced WMMSE algorithm to solve the JCPA problem in multi-channel wireless networks.<n>We then introduce JCPGNN-M, a graph neural network-based solution that enables simultaneous multi-channel allocation for each user.<n>We show that JCPGNN-M achieves better data rate compared to eWMMSE.
  arXiv  Detail & Related papers  (2025-06-04T10:34:05Z)
• Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning [1.9120720496423733]
  We introduce a Transformer-empowered actor-critic framework specifically designed for sequence-aware SFC partitioning.<n>Our approach effectively models complex inter-dependencies among VNFs, facilitating coordinated and parallelized decision-making processes.
  arXiv  Detail & Related papers  (2025-04-26T12:18:57Z)
• Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networks [55.467288506826755]
  Federated learning (FL) has been recognized as a viable solution for local-privacy-aware collaborative model training in wireless edge networks.<n>Most existing communication-efficient FL algorithms fail to reduce the significant inter-device variance.<n>We propose a novel communication-efficient FL algorithm, named FedQVR, which relies on a sophisticated variance-reduced scheme.
  arXiv  Detail & Related papers  (2025-01-20T04:26:21Z)
• Optimization Guarantees of Unfolded ISTA and ADMM Networks With Smooth Soft-Thresholding [57.71603937699949]
  We study optimization guarantees, i.e., achieving near-zero training loss with the increase in the number of learning epochs. We show that the threshold on the number of training samples increases with the increase in the network width.
  arXiv  Detail & Related papers  (2023-09-12T13:03:47Z)
• Scalable Resource Management for Dynamic MEC: An Unsupervised Link-Output Graph Neural Network Approach [36.32772317151467]
  Deep learning has been successfully adopted in mobile edge computing (MEC) to optimize task offloading and resource allocation. The dynamics of edge networks raise two challenges in neural network (NN)-based optimization methods: low scalability and high training costs. In this paper, a novel link-output GNN (LOGNN)-based resource management approach is proposed to flexibly optimize the resource allocation in MEC.
  arXiv  Detail & Related papers  (2023-06-15T08:21:41Z)
• State-Augmented Learnable Algorithms for Resource Management in Wireless Networks [124.89036526192268]
  We propose a state-augmented algorithm for solving resource management problems in wireless networks. We show that the proposed algorithm leads to feasible and near-optimal RRM decisions.
  arXiv  Detail & Related papers  (2022-07-05T18:02:54Z)
• Comparative Analysis of Interval Reachability for Robust Implicit and Feedforward Neural Networks [64.23331120621118]
  We use interval reachability analysis to obtain robustness guarantees for implicit neural networks (INNs) INNs are a class of implicit learning models that use implicit equations as layers. We show that our approach performs at least as well as, and generally better than, applying state-of-the-art interval bound propagation methods to INNs.
  arXiv  Detail & Related papers  (2022-04-01T03:31:27Z)
• Algorithm Unrolling for Massive Access via Deep Neural Network with Theoretical Guarantee [30.86806523281873]
  Massive access is a critical design challenge of Internet of Things (IoT) networks. We consider the grant-free uplink transmission of an IoT network with a multiple-antenna base station (BS) and a large number of single-antenna IoT devices. We propose a novel algorithm unrolling framework based on the deep neural network to simultaneously achieve low computational complexity and high robustness.
  arXiv  Detail & Related papers  (2021-06-19T05:23:05Z)
• Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles [52.79089414630366]
  We develop a novel deep cooperative NOMA scheme, drawing upon the recent advances in deep learning (DL) We develop a novel hybrid-cascaded deep neural network (DNN) architecture such that the entire system can be optimized in a holistic manner.
  arXiv  Detail & Related papers  (2020-07-27T12:38:37Z)
• Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systems [59.804810122136345]
  We propose a framework for deep-unfolding, where a general form of iterative algorithm induced deep-unfolding neural network (IAIDNN) is developed. An efficient IAIDNN based on the structure of the classic weighted minimum mean-square error (WMMSE) iterative algorithm is developed. We show that the proposed IAIDNN efficiently achieves the performance of the iterative WMMSE algorithm with reduced computational complexity.
  arXiv  Detail & Related papers  (2020-06-15T02:57:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.