Consensus Protocols for Entanglement-Aware Scheduling in Distributed Quantum Neural Networks

2026-02-06

AI Summary

This work addresses the robustness and efficiency bottlenecks in distributed quantum neural networks over the quantum internet, which stem from the fragility of entanglement and challenges in synchronized training. To overcome these limitations, the authors propose the CEAS framework, which co-designs a quantum consensus protocol with an adaptive entanglement management mechanism. CEAS uniquely integrates fidelity-weighted parameter aggregation, decoherence-aware Bell pair scheduling based on an exponential decay model, and quantum-authenticated Byzantine fault tolerance, all while respecting the constraints of NISQ-era devices and ensuring security. Theoretical analysis establishes convergence under heterogeneous noise conditions, and simulations demonstrate that CEAS improves model accuracy by 10–15 percentage points over baseline methods under Byzantine attacks while achieving a 90% Bell pair utilization rate.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Distributed Search
• Multiagent Systems: Adversarial Agents

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Consent frameworks and practices on the web

Abstract

The realization of distributed quantum neural networks (DQNNs) over quantum internet infrastructures faces fundamental challenges arising from the fragile nature of entanglement and the demanding synchronization requirements of distributed learning. We introduce a Consensus-Entanglement-Aware Scheduling (CEAS) framework that co-designs quantum consensus protocols with adaptive entanglement management to enable robust synchronous training across distributed quantum processors. CEAS integrates fidelity-weighted aggregation, in which parameter updates are weighted by quantum Fisher information to suppress noisy contributions, with decoherence-aware entanglement scheduling that treats Bell pairs as perishable resources subject to exponential decay. The framework incorporates quantum-authenticated Byzantine fault tolerance, ensuring security against malicious nodes while maintaining compatibility with noisy intermediate-scale quantum (NISQ) constraints. Our theoretical analysis establishes convergence guarantees under heterogeneous noise conditions, while numerical simulations demonstrate that CEAS maintains 10-15 percentage points higher accuracy compared to entanglement-oblivious baselines under coordinated Byzantine attacks, achieving 90 percent Bell-pair utilization despite coherence time limitations. This work provides a foundational architecture for scalable distributed quantum machine learning, bridging quantum networking, distributed optimization, and early fault-tolerant quantum computation.

Problem

• distributed quantum neural networks
• entanglement fragility
• synchronization requirements
• quantum consensus
• decoherence

Innovation

• Consensus Protocol
• Entanglement-Aware Scheduling
• Quantum Byzantine Fault Tolerance
• Fidelity-Weighted Aggregation
• Distributed Quantum Neural Networks