Graph Neural Networks for Resource Allocation in Integrated Sensing and Communication
Abstract
In vehicular integrated sensing and communication (ISAC) networks, each service-provider vehicle uses a limited power budget to serve multiple sensing targets and communication receivers. Maximizing the communication sum-rate subject to sensing signal-to-interference-plus-noise ratio (SINR) constraints is nonconvex, and iterative optimization is costly to rerun for every network layout. This paper proposes a graph neural network (GNN)-based power allocation algorithm, termed GNN-ISAC. Concretely, GNN-ISAC addresses the aforementioned problem by considering two distinct edge types in the graph representation, one capturing the inter-provider interference, the other representing the intra-provider power-budget sharing. GNN-ISAC is trained without labels using a sensing-penalized sum-rate loss. We also adapt the weighted mean-square error minimization (WMMSE) algorithm to this problem by introducing a sensing-power reservation step. Simulation results show that GNN-ISAC achieves communication sum-rates close to WMMSE with low sensing-link violation rates and much less computation. It also outperforms an existing heterogeneous GNN and a channel-blind baseline, and generalizes to larger networks without retraining.
Related
- CRB-Guided Sensing and Resource Allocation for Human Pose Prediction in Integrated Sensing, Communication, and Computation Systems
- Performance Analysis and Sensing-Aware Resource Allocation for Full-Duplex Massive MIMO ISCC Networks
- Quantum Annealing for Resource Allocation in Next-Generation Wireless Communication Networks: A QUBO Modeling Guide
- A Token/KV-Cache Communication Media Selection and Resource Allocation Strategy for Multi-Agent Collaboration
- An Inertial Split Feasibility Framework for Bandwidth Allocation Problems in Communication Networks
BibTeX
@misc{liao2026graph,
title = {{Graph Neural Networks for Resource Allocation in Integrated Sensing and Communication}},
author = {Junyu Liao and Lili Chen and Tian Han and Jamie Evans},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07277},
eprint = {2611.07277},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07277},
}
RIS
TY - UNPB
TI - Graph Neural Networks for Resource Allocation in Integrated Sensing and Communication
AU - Junyu Liao
AU - Lili Chen
AU - Tian Han
AU - Jamie Evans
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.07277
UR - https://arxiv.org/abs/2611.07277
AB - In vehicular integrated sensing and communication (ISAC) networks, each service-provider vehicle uses a limited power budget to serve multiple sensing targets and communication receivers. Maximizing the communication sum-rate subject to sensing signal-to-interference-plus-noise ratio (SINR) constraints is nonconvex, and iterative optimization is costly to rerun for every network layout. This paper proposes a graph neural network (GNN)-based power allocation algorithm, termed GNN-ISAC. Concretely, GNN-ISAC addresses the aforementioned problem by considering two distinct edge types in the graph representation, one capturing the inter-provider interference, the other representing the intra-provider power-budget sharing. GNN-ISAC is trained without labels using a sensing-penalized sum-rate loss. We also adapt the weighted mean-square error minimization (WMMSE) algorithm to this problem by introducing a sensing-power reservation step. Simulation results show that GNN-ISAC achieves communication sum-rates close to WMMSE with low sensing-link violation rates and much less computation. It also outperforms an existing heterogeneous GNN and a channel-blind baseline, and generalizes to larger networks without retraining.
ER -