Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks

2025-10-13

AI Summary

To address the urgent need for differentiated QoS provisioning and scalable multicast routing in 6G networks supporting bandwidth-intensive real-time streaming (e.g., volumetric video, multi-sensory XR), this paper proposes a graph neural network (GNN)-based intelligent multicast routing framework. Methodologically, routing is formulated as a constrained minimum-flow optimization problem; path reuse mechanisms and reinforcement learning are integrated to enable sequential multicast tree construction. A Graph Attention Network (GAT) encodes network topology, while an LSTM captures temporal dependencies; the entire architecture jointly optimizes transmission cost and user-specific video quality in an end-to-end manner. Compared to conventional algorithms, our approach significantly reduces computational complexity while closely approximating dynamic programming-optimal solutions. It exhibits strong topological generalization, dynamic adaptability, and real-time deployability—demonstrated via extensive evaluation on large-scale, heterogeneous, and time-varying networks, confirming both efficiency and scalability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

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.

Problem

• Optimizing multicast routing for bandwidth-intensive 6G streaming services
• Addressing scalability and QoS heterogeneity in network resource allocation
• Enhancing topological generalization in neural network-based routing solutions

Innovation

• Graph neural network framework for multicast routing
• Reinforcement learning constructs adaptive multicast trees
• Graph attention network with LSTM handles network dynamics