Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
Xiucheng Wang, Zien Wang, Nan Cheng, Wenchao Xu, Wei Quan, Xuemin Shen
TL;DR
This work tackles the challenge of multicast routing for 6G networks with heterogeneous QoS demands by formulating routing as a constrained minimum-flow problem and solving it with a graph neural network–based planner. The proposed Graph Policy Network combines a Graph Attention Network encoder with an LSTM-based path history module to sequentially construct tree-like multicast deliveries while reusing shared paths, guided by a policy-gradient objective. The approach yields near-optimal transmission costs, scales linearly with network size, and generalizes across dynamic topologies, enabling real-time deployment for large-scale, differentiated video streaming. Empirical results on synthetic networks show substantial gains in inference speed and competitive routing efficiency compared to traditional optimization and heuristic baselines, underscoring its practical impact for 6G multimedia delivery.
Abstract
The increase of bandwidth-intensive applications in sixth-generation (6G) wireless networks, such as real-time volumetric streaming and multi-sensory extended reality, demands intelligent multicast routing solutions capable of delivering differentiated quality-of-service (QoS) at scale. Traditional shortest-path and multicast routing algorithms are either computationally prohibitive or structurally rigid, and they often fail to support heterogeneous user demands, leading to suboptimal resource utilization. Neural network-based approaches, while offering improved inference speed, typically lack topological generalization and scalability. To address these limitations, this paper presents a graph neural network (GNN)-based multicast routing framework that jointly minimizes total transmission cost and supports user-specific video quality requirements. The routing problem is formulated as a constrained minimum-flow optimization task, and a reinforcement learning algorithm is developed to sequentially construct efficient multicast trees by reusing paths and adapting to network dynamics. A graph attention network (GAT) is employed as the encoder to extract context-aware node embeddings, while a long short-term memory (LSTM) module models the sequential dependencies in routing decisions. Extensive simulations demonstrate that the proposed method closely approximates optimal dynamic programming-based solutions while significantly reducing computational complexity. The results also confirm strong generalization to large-scale and dynamic network topologies, highlighting the method's potential for real-time deployment in 6G multimedia delivery scenarios. Code is available at https://github.com/UNIC-Lab/GNN-Routing.