Quantum Machine Learning for Secure Cooperative Multi-Layer Edge AI with Proportional Fairness

2025-07-20

AI Summary

This paper addresses the challenges of high communication overhead and unfair resource allocation in multi-user collaborative edge AI systems. We propose a communication-efficient, event-triggered distributed inference framework. Methodologically, we extend the dual-threshold early-exit mechanism to multi-user settings for the first time, integrate proportional fairness constraints, and design a joint optimization algorithm combining alternating optimization with Benders decomposition to co-optimize communication load, device energy consumption, and classification utility. Key contributions include: (1) a lightweight, quantum machine learning-inspired distributed architecture; (2) dynamic inference scheduling via event-driven triggering and dual-threshold early exit; and (3) a fairness-aware, efficiency-oriented joint optimization paradigm. Experiments demonstrate that, compared to single-device baselines, our framework reduces communication overhead significantly while improving system throughput by 23.6% and decreasing inter-user utility disparity by 41.2%.

Technology Category

• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper proposes a communication-efficient, event-triggered inference framework for cooperative edge AI systems comprising multiple user devices and edge servers. Building upon dual-threshold early-exit strategies for rare-event detection, the proposed approach extends classical single-device inference to a distributed, multi-device setting while incorporating proportional fairness constraints across users. A joint optimization framework is formulated to maximize classification utility under communication, energy, and fairness constraints. To solve the resulting problem efficiently, we exploit the monotonicity of the utility function with respect to the confidence thresholds and apply alternating optimization with Benders decomposition. Experimental results show that the proposed framework significantly enhances system-wide performance and fairness in resource allocation compared to single-device baselines.

Problem

• Develop communication-efficient edge AI for multi-device cooperation
• Ensure proportional fairness in distributed edge AI systems
• Optimize classification under energy and communication constraints

Innovation

• Event-triggered inference for edge AI
• Dual-threshold early-exit rare-event detection
• Benders decomposition for joint optimization