A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints
Authors: Yikun Wang, Yang Li, Yik-Chung Wu, Rui Zhang
Organizations: Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong · School of Computing and Information Technology, Great Bay University, Dongguan 523000, China · Department of Electrical and Computer Engineering, National University of Singapore, Singapore
While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient issue in backpropagation, the difficulty of enforcing intricate constraints with discrete variables, and the inability in generating solutions with non-same-parameter-same-decision (non-SPSD) property. To address these challenges, this paper proposes a general DL framework by introducing the support set to represent the discrete variables. We model the elements of the support set as random variables and learn their joint probability distribution. By factorizing the joint probability as the product of conditional probabilities, each conditional probability is sequentially learned. This probabilistic modeling directly tackles all the aforementioned challenges of DL for handling discrete variables. By operating on probability distributions instead of hard binary decisions, the framework naturally avoids the zero-gradient issue. During the learning of the conditional probabilities, discrete constraints can be seamlessly enforced by masking out infeasible solutions. Moreover, with a dynamic context embedding that captures the evolving discrete solutions, the non-SPSD property is inherently provided by the proposed framework. We apply the proposed framework to two representative mixed-discrete wireless resource allocation problems: (a) joint user association and beamforming in cell-free systems, and (b) joint antenna positioning and beamforming in movable antenna-aided systems. Simulation results demonstrate that the proposed DL framework consistently outperforms existing baselines in terms of both system performance and computational efficiency.
Figures & tables
Fig. 1: Illustrations of two typical examples of mixed-discrete wireless resource allocation problems.
Fig. 2: The overall architecture of the proposed DL framework.
Fig. 3: Overview of the DVLN.
Method
Feasibility for coupled discrete constraints
Non-SPSD handling
Joint training without relaxation
[ 23 ]
N/A, no coupled discrete constraints
✗, not explicitly considered
✗, discrete variables only
SGNN [ 25 ]
✗, usually requiring post-hoc projection or repair
✓, through sequential block generation
✗, due to softmax relaxation
STE
✗, usually requiring post-hoc projection or repair
✗, parallel-output structure
Partial, due to biased gradient approximation
Gumbel-Softmax
✗, usually requiring post-hoc projection or repair
✗, parallel-output structure
Partial, due to approximation error
Proposed
✓, through support-set reformulation and constraint-aware masking
✓, through non-SPSD-aware context embedding with dynamic attention
✓, through joint unsupervised training without relaxation
TABLE I: Comparison of learning-based methods for wireless resource allocation
Fig. 4: The network architecture in Example 1.
Figure 6Figure 7
Fig. 11: Sum rate performance under imperfect CSI.
Fig. 12: The sum rate performance comparison under different power budgets, M ’s, and N ’s.
Fig. 13: The average computation time comparison when M=6 and N=49 .
The aggressive densification of modern wireless networks necessitates judicious resource allocation to mitigate severe mutual interference. However, classical iterative algorithms remain computationally prohibitive for real-time applications requiring rapid responsiveness. While recent deep learning-based methods show promise, they typically function as task-specific solvers lacking the flexibility to adapt to different objectives and scenarios without expensive retraining. To address these limitations, we propose a graph foundation model for resource allocation (GFM-RA) based on a pre-training and fine-tuning paradigm to extract unified representations, thereby enabling rapid adaptation to different objectives and scenarios. Specifically, we introduce an interference-aware Transformer architecture with a bias projector that injects interference topologies into global attention mechanisms. Furthermore, we develop a hybrid self-supervised pre-training strategy that synergizes masked edge prediction with negative-free Teacher-Student contrastive learning, enabling the model to capture transferable structural representations from massive unlabeled datasets. Extensive experiments demonstrate that the proposed framework achieves state-of-the-art performance and scales effectively with increased model capacity. Crucially, leveraging its unified representations, the foundation model exhibits exceptional sample efficiency, enabling robust few-shot adaptation to diverse and unsupervised downstream objectives in out-of-distribution (OOD) scenarios. These results demonstrate the promise of pre-trained foundation models for adaptable wireless resource allocation and provide a strong foundation for future research on generalizable learning-based wireless optimization.
Yucheng Sheng, Jiacheng Wang, Le Liang +2
National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China · Department of Electrical and Computer Engineering, University of California, Santa Cruz, CA 95064, USA
Next-generation wireless networks, including satellite-to-Open RAN systems, demand agile and intelligent resource management capable of handling dynamic multi-user interference under stochastic quality of service constraints. This paper introduces DIFFRACT, a neuralized utility maximization framework that leverages differentiable programming to integrate deep learning with optimization in wireless networks. Central to our approach is the exploitation of the mathematical structure of standard interference functions, which are foundational in wireless power control. By developing a duality theory for these functions, we map iterative interference management algorithms into differentiable neural network architectures via algorithm unrolling. This enables distributed, end-to-end gradient-based learning at the network edge, supporting real-time adaptation to interference in both terrestrial and non-terrestrial environments. DIFFRACT allows for scalable and robust utility maximization by modeling complex channel dynamics and leveraging the expressiveness of differentiable models. Experimental results confirm the framework's theoretical soundness and practical effectiveness for next-generation wireless systems.
Chee Wei Tan, Siya Chen
Nanyang Technological University, Singapore, Nanyang Ave., Singapore · Department of Computer Science, City University of Hong Kong, Hong Kong
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.