Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems

Mengru Wu, Jiawei Li, Jiaqi Wei, Bin Lyu, Kai-Kit Wong, Hyundong Shin

TL;DR

An anti-jamming collaborative inference system in the presence of a malicious jammer is focused on, which maximizes the system's revenue of delay and accuracy (RDA) under inference accuracy and computing resource constraints by jointly optimizing computation resource allocation, devices'transmit power, and DNN partitioning.

Abstract

With the increasing computational demands of deep neural network (DNN) inference on resource-constrained devices, DNN partitioning-based device-edge collaborative inference has emerged as a promising paradigm. However, the transmission of intermediate feature data is vulnerable to malicious jamming, which significantly degrades the overall inference performance. To counter this threat, this letter focuses on an anti-jamming collaborative inference system in the presence of a malicious jammer. In this system, a DNN model is partitioned into two distinct segments, which are executed by wireless devices and edge servers, respectively. We first analyze the effects of jamming and DNN partitioning on inference accuracy via data regression. Based on this, our objective is to maximize the system's revenue of delay and accuracy (RDA) under inference accuracy and computing resource constraints by jointly optimizing computation resource allocation, devices' transmit power, and DNN partitioning. To address the mixed-integer nonlinear programming problem, we propose an efficient alternating optimization-based algorithm, which decomposes the problem into three subproblems that are solved via Karush-Kuhn-Tucker conditions, convex optimization methods, and a quantum genetic algorithm, respectively. Extensive simulations demonstrate that our proposed scheme outperforms baselines in terms of RDA.

Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems

TL;DR

An anti-jamming collaborative inference system in the presence of a malicious jammer is focused on, which maximizes the system's revenue of delay and accuracy (RDA) under inference accuracy and computing resource constraints by jointly optimizing computation resource allocation, devices'transmit power, and DNN partitioning.

Abstract

With the increasing computational demands of deep neural network (DNN) inference on resource-constrained devices, DNN partitioning-based device-edge collaborative inference has emerged as a promising paradigm. However, the transmission of intermediate feature data is vulnerable to malicious jamming, which significantly degrades the overall inference performance. To counter this threat, this letter focuses on an anti-jamming collaborative inference system in the presence of a malicious jammer. In this system, a DNN model is partitioned into two distinct segments, which are executed by wireless devices and edge servers, respectively. We first analyze the effects of jamming and DNN partitioning on inference accuracy via data regression. Based on this, our objective is to maximize the system's revenue of delay and accuracy (RDA) under inference accuracy and computing resource constraints by jointly optimizing computation resource allocation, devices' transmit power, and DNN partitioning. To address the mixed-integer nonlinear programming problem, we propose an efficient alternating optimization-based algorithm, which decomposes the problem into three subproblems that are solved via Karush-Kuhn-Tucker conditions, convex optimization methods, and a quantum genetic algorithm, respectively. Extensive simulations demonstrate that our proposed scheme outperforms baselines in terms of RDA.
Paper Structure (13 sections, 25 equations, 5 figures, 1 algorithm)

This paper contains 13 sections, 25 equations, 5 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. DNN Partitioning-based CI
  5. IFD Transmission
  6. Inference Accuracy Model
  7. Problem Formulation
  8. Proposed Solution
  9. Computation Resource Allocation Subproblem
  10. Transmit Power Optimization Subproblem
  11. DNN Partitioning Subproblem
  12. Simulation Results
  13. Conclusion

Figures (5)

  • Figure 1: A device-edge CI system.
  • Figure 2: Partitioning points of ResNet 18.
  • Figure 3: Data fitting of ResNet 18 on the CIFAR 10 dataset.
  • Figure 4: Performance with respect to each device's computing capability: (a) RDA. (b) Total task inference delay. (c) Average accuracy.
  • Figure 5: Performance with respect to jamming power: (a) RDA. (b) Total task inference delay. (c) Average accuracy.