Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2603.02579 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918367333449728 |
|---|---|
| author | Wu, Mengru Li, Jiawei Wei, Jiaqi Lyu, Bin Wong, Kai-Kit Shin, Hyundong |
| author_facet | Wu, Mengru Li, Jiawei Wei, Jiaqi Lyu, Bin Wong, Kai-Kit Shin, Hyundong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02579 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems Wu, Mengru Li, Jiawei Wei, Jiaqi Lyu, Bin Wong, Kai-Kit Shin, Hyundong Machine Learning Systems and Control 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. |
| title | Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems |
| topic | Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2603.02579 |