# Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge Intelligence

arXiv: https://arxiv.org/abs/2609.15847 · HTML: https://mlsanity.com/paper/2609.15847/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 14 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [The power of quantum neural networks](https://mlsanity.com/paper/2011.00027/) (2020)
- [Resource Allocation for Multiuser Edge Inference with Batching and Early Exiting (Extended Version)](https://mlsanity.com/paper/2204.05223/) (2022)
- [Energy-based Proportional Fairness in Cooperative Edge Computing](https://mlsanity.com/paper/2201.00910/) (2022)
- [Joint Semantic Transmission and Resource Allocation for Intelligent Computation Task Offloading in MEC Systems](https://mlsanity.com/paper/2503.08001/) (2025)

## Abstract (arXiv)

This paper proposes FREDI (Fair Resource Allocation for Edge Dual-Threshold Inference), a secure wireless edge-intelligence framework for event-triggered inference in a cooperative user equipment (UE)--edge server (ES)--cloud system. Each UE performs early-exit convolutional neural network (CNN) screening using dual confidence thresholds, while critical events are securely offloaded to an edge server for detailed classification. We formulate a proportionally-fair utility maximization problem that jointly optimizes UE--ES association, wireless and processing resources, and confidence thresholds. FREDI decomposes the problem into proportional-fair resource allocation and dual-threshold inference optimization. We prove that the detected-critical event set is set-monotone non-increasing in both thresholds, and exploit the finite empirical confidence domain for exact threshold optimization. An empirical resource--utility response envelope yields a computable global suboptimality bound and a sufficient condition for global optimality. By pre-eliminating infeasible UE--ES pairs and exactly projecting out bandwidth and transmit-power variables, the resource-allocation subproblem is reduced to a mixed-integer exponential-cone program solvable to the certified global optimality within a prescribed gap. Numerical results with early-exit MobileNetV2 and ShuffleNetV2 demonstrate near-perfect UE fairness with aggregate utility close to a Sum-Utility benchmark, reveal security-induced resource fragmentation, and demonstrate the Stage-A scalability from 6 to 144 UEs with median solving time below 0.1~s in the tested configurations.