Graph Learning for Cooperative Cell-Free ISAC Systems: From Optimization to Estimation

TL;DR

This paper introduces graph learning methods for cell-free ISAC systems, enabling joint optimization and estimation, leading to improved accuracy and efficiency in multi-target sensing and communication.

Contribution

It proposes two novel graph learning frameworks, dynamic graph learning and mirror-GAT, for unified system design and estimation in cell-free ISAC networks.

Findings

Both frameworks outperform traditional methods in estimation accuracy.

Mirror-GAT significantly reduces computational complexity and signaling overhead.

Dynamic graph learning enhances robustness and performance in diverse environments.

Abstract

Cell-free integrated sensing and communication (ISAC) systems have emerged as a promising paradigm for sixth-generation (6G) networks, enabling simultaneous high-rate data transmission and high-precision radar sensing through cooperative distributed access points (APs). Fully exploiting these capabilities requires a unified design that bridges system-level optimization with multi-target parameter estimation. This paper proposes an end-to-end graph learning approach to close this gap, modeling the entire cell-free ISAC network as a heterogeneous graph to jointly design the AP mode selection, user association, precoding, and echo signal processing for multi-target position and velocity estimation. In particular, we propose two novel heterogeneous graph learning frameworks: a dynamic graph learning framework and a lightweight mirror-based graph attention network (mirror-GAT) framework. The dynamic graph learning framework employs structural and temporal attention mechanisms integrated with a three-dimensional convolutional neural network (3D-CNN), enabling superior performance and robustness in cell-free ISAC environments. Conversely, the mirror-GAT framework significantly reduces computational complexity and signaling overhead through a bi-level iterative structure with share adjacency. Simulation results validate that both proposed graph-learning-based frameworks achieve significant improvements in multi-target position and velocity estimation accuracy compared to conventional heuristic and optimization-based designs. Particularly, the mirror-GAT framework demonstrates substantial reductions in computational time and signaling overhead, underscoring its suitability for practical deployments.