RELiQ: Scalable Entanglement Routing via Reinforcement Learning in Quantum Networks

2025-11-27

AI Summary

In quantum networks, entanglement routing faces challenges including highly dynamic links, probabilistic operations, and absence of global topology knowledge, rendering conventional heuristic and learning-based approaches insufficient in balancing scalability and robustness. This paper proposes a distributed routing framework that synergistically integrates graph neural networks (GNNs) and reinforcement learning (RL): GNNs model local topology and generalize to unseen network structures, while RL performs online policy optimization based on local observations and message-passing. The method operates without global topology awareness, mitigates overfitting, and enables rapid topology adaptation. Experiments on both synthetic and real-world topologies demonstrate that our approach outperforms existing local heuristics and learning-based methods, and matches or even surpasses traditional global-information-dependent algorithms in routing performance.

Technology Category

• Planning, Routing, and Scheduling: Routing
• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Quantum networks are becoming increasingly important because of advancements in quantum computing and quantum sensing, such as recent developments in distributed quantum computing and federated quantum machine learning. Routing entanglement in quantum networks poses several fundamental as well as technical challenges, including the high dynamicity of quantum network links and the probabilistic nature of quantum operations. Consequently, designing hand-crafted heuristics is difficult and often leads to suboptimal performance, especially if global network topology information is unavailable. In this paper, we propose RELiQ, a reinforcement learning-based approach to entanglement routing that only relies on local information and iterative message exchange. Utilizing a graph neural network, RELiQ learns graph representations and avoids overfitting to specific network topologies - a prevalent issue for learning-based approaches. Our approach, trained on random graphs, consistently outperforms existing local information heuristics and learning-based approaches when applied to random and real-world topologies. When compared to global information heuristics, our method achieves similar or superior performance because of its rapid response to topology changes.

Problem

• Routing entanglement in dynamic quantum networks
• Overcoming probabilistic quantum operation challenges
• Avoiding overfitting to specific network topologies

Innovation

• Reinforcement learning for entanglement routing
• Graph neural network for topology generalization
• Local information with iterative message exchange