App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 12

Test case selection for deep neural network via multi-objective optimization

Wang Fengying1,2
Wei Xingling1
Du Liming2
Zhang Yan2
Li Junke2
1. School of Computer Science and Engineering, Shenyang Jianzhu University, Shenyang 110168, China
2. School of Information Engineering, Suqian University, Suqian Jiangsu 223800, China
DOI: 10.19734/j.issn.1001-3695.2026.04.0123

Abstract

In deep neural network testing, discovering potential faults in a model requires a large number of labeled test cases, incurring exceptionally high annotation costs. To address this issue, this paper proposed a multi-objective optimization-based test case selection method named MOTCS. MOTCS aimed to reduce annotation costs by prioritizing the selection of test cases with high fault-revealing capability from large-scale unlabeled data, thereby improving testing efficiency. MOTCS used uncertainty and fault behavior diversity indicators to guide the search and employed a customized NSGA-II algorithm to perform multi-objective search, prioritizing test cases with high uncertainty and diverse fault behaviors to trigger as many faults as possible and maximize the revelation of different fault types in the model. Experimental results on 12 evaluation subjects constructed from 4 datasets and 5 DNN models showed that, compared with 8 representative baseline methods, MOTCS achieved the highest fault detection rate in 83.3% of the evaluation scenarios, attained optimal fault diversity coverage in all evaluation scenarios, and performed best in model repair through retraining. These results demonstrate the effectiveness of MOTCS in the task of test case selection.

Foundation Support

国家自然科学基金资助项目(62262055)
江苏省产学研合作项目(BY20251032、BY20251033)
宿迁市指导性科技计划项目(Z2025040)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.04.0123
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 12

Publish History

[2026-08-21] Accepted Paper

Cite This Article

王凤英, 魏星铃, 杜利明, 等. 基于多目标优化的深度神经网络测试用例选择方法 [J]. 计算机应用研究, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0123. (Wang Fengying, Wei Xingling, Du Liming, et al. Test case selection for deep neural network via multi-objective optimization [J]. Application Research of Computers, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.04.0123. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)