A Graph Foundation Model for Wireless Resource Allocation

2026-04-08

AI Summary

This work addresses the severe performance degradation caused by mutual interference in dense wireless networks, a challenge exacerbated by existing approaches that either incur high computational overhead or exhibit limited generalization. To overcome these limitations, the paper proposes GFM-RA, a graph foundation model tailored for wireless resource allocation. Built upon a pretrain-finetune paradigm, GFM-RA leverages an interference-aware Transformer architecture and a hybrid self-supervised pretraining strategy—combining masked edge prediction with negative-sample-free teacher-student contrastive learning—to extract transferable structural representations from unlabeled data. Without requiring extensive retraining, the model rapidly adapts to out-of-distribution scenarios for diverse multi-objective resource allocation tasks, achieving state-of-the-art performance across multiple downstream benchmarks while significantly enhancing sample efficiency, generalization, and robustness.

Abstract

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.

Problem

• wireless resource allocation
• mutual interference
• real-time responsiveness
• adaptability
• foundation model

Innovation

• Graph Foundation Model
• Interference-Aware Transformer
• Self-Supervised Pre-training
• Wireless Resource Allocation
• Few-Shot Adaptation