收藏切换
Using Deep Learning to Assist Algorithm Design—Taking Course Scheduling Problem and Traveling Salesman Problem as Examples
收藏切换
Jingyan Sui1, Shizhe Ding2, 3, Boyang Xia2, 3, Ruizhi Liu2, 3, Zhenxin Ding2, 3, Liming Xu2, 3, Rui Wang2, 3, Xulin Huang2, Jiepeng Li2, 3, 5, Haicang Zhang2, 3, Chungong Yu2, 3, Chao Wang2, 3, Dongbo Bu2, 3, 4, *
Journal of Computer Research and Development | 2026, 63(7) : 1670 - 1689
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(7): 1670-1689
• Special Issue on “AI4Science: A New Paradigm in Scientific Research” •
Using Deep Learning to Assist Algorithm Design—Taking Course Scheduling Problem and Traveling Salesman Problem as Examples
Full
Jingyan Sui1, Shizhe Ding2, 3, Boyang Xia2, 3, Ruizhi Liu2, 3, Zhenxin Ding2, 3, Liming Xu2, 3, Rui Wang2, 3, Xulin Huang2, Jiepeng Li2, 3, 5, Haicang Zhang2, 3, Chungong Yu2, 3, Chao Wang2, 3, Dongbo Bu2, 3, 4, *
Affiliations
  • 1School of Artificial Intelligence and Computer Science, Liaocheng University, Liaocheng, Shandong 252000
  • 2State Key Lab of Processors (Institute of Computing, Chinese Academy of Sciences), Beijing 100190
  • 3University of Chinese Academy of Sciences, Beijing 100049
  • 4Central China Artificial Intelligence Research Institute, Zhengzhou 450046
  • 5Hangzhou Institute for Advanced Study, UCAS, Hangzhou 310024
  • born in 1982. PhD. Her main research interests include algorithm design, machine learning, deep learning, combinatorial optimization and bioinformatics

    born in 1998. PhD. His main research interests include machine learning and combinatorial optimization

    born in 1998. Master. His main research interests include machine learning and combinatorial optimization

    born in 1996. PhD. His main research interests include open-source EDA, AI for EDA, algorithm design, and combinatorial optimization

    born in 1994. Master. His main research interests include algorithm design, machine learning, and combinatorial optimization

    born in 1997. Master. Her main research interests include algorithm design, machine learning, and combinatorial optimization

    born in 2001. PhD candidate. Her main research interests include algorithm design, machine learning, deep learning, and combinatorial optimization

    born in 1998. Master. His main research interests include algorithm design, machine learning, deep learning, and protein design

    born in 2000. Master. His main research interests include algorithm design, large language model, and reinforcement learning

    born in 1987. PhD. His main research interests include machine learning, protein design, and protein structure prediction

    born in 1979. Master. His main research interests include bioinfomatics and protein structure prediction

    born in 1987. PhD. His main research interests include algorithm design, deep learning, knowledge graph, and automonous driving

    born in 1973. PhD, professor, PhD supervisor. His main research interests include algorithm design, bioinformatics, protein structure prediction, and deep learning

About Author:

born in 1982. PhD. Her main research interests include algorithm design, machine learning, deep learning, combinatorial optimization and bioinformatics

born in 1998. PhD. His main research interests include machine learning and combinatorial optimization

born in 1998. Master. His main research interests include machine learning and combinatorial optimization

born in 1996. PhD. His main research interests include open-source EDA, AI for EDA, algorithm design, and combinatorial optimization

born in 1994. Master. His main research interests include algorithm design, machine learning, and combinatorial optimization

born in 1997. Master. Her main research interests include algorithm design, machine learning, and combinatorial optimization

born in 2001. PhD candidate. Her main research interests include algorithm design, machine learning, deep learning, and combinatorial optimization

born in 1998. Master. His main research interests include algorithm design, machine learning, deep learning, and protein design

born in 2000. Master. His main research interests include algorithm design, large language model, and reinforcement learning

born in 1987. PhD. His main research interests include machine learning, protein design, and protein structure prediction

born in 1979. Master. His main research interests include bioinfomatics and protein structure prediction

born in 1987. PhD. His main research interests include algorithm design, deep learning, knowledge graph, and automonous driving

born in 1973. PhD, professor, PhD supervisor. His main research interests include algorithm design, bioinformatics, protein structure prediction, and deep learning

Published: 2026-07-01 doi: 10.7544/issn1000-1239.202660017
Outline
收藏切换

Deep learning has recently demonstrated strong capabilities in pattern discovery and structural inference, offering new possibilities for algorithm design—a field traditionally reliant on human experience and intuition. We focus on the core objective of automatically learning interpretable algorithmic rules under unsupervised settings, using two representative combinatorial optimization problems as cases: course scheduling problem (CSP) and traveling salesman problem (TSP). We propose two deep reinforcement–based methods, Neural-Greedy and Neural-3-OPT. For CSP, Neural-Greedy autonomously learns three optimal greedy rules from large collections of problem instances: prioritizing courses with the earliest finishing times, the latest starting times, and a hybrid of the two. Its underlying mechanism lies in parameter modulation and neuron cooperation, which precisely focuses on critical temporal features and enables the simultaneous acquisition of multiple rules. For TSP, Neural-3-OPT learns efficient 3-opt heuristic autonomously from large collections of problem instances, achieving optimality gaps as low as 0.00%, 0.08%, and 0.74% on random TSP20, TSP50, and TSP100 datasets, respectively. It significantly outperforms the industrial solver OR-Tools and maintains superior performance on the real-world TSPLIB benchmark. This advantage stems from an intelligent decision mechanism of early-stage precise selection, which prioritizes inefficient edges with substantial impact on global solution quality and identifies reconnection strategies adaptive to the entire iterative process, thereby avoiding myopic greedy choices and ineffective iterations to achieve fast convergence and high-quality solutions. Overall, our results demonstrate that deep learning can not only approach optimal solution quality but also autonomously learn interpretable algorithmic rules, offering a data-driven paradigm for algorithm design and providing important insights into the development of AI-assisted algorithm design.

algorithm design  /  deep learning  /  greedy rule  /  heuristic rule  /  course scheduling problem  /  traveling salesman problem  /  neural network
隋京言, 丁诗哲, 夏博洋, 刘睿之, 丁振欣, 徐黎明, 王睿, 黄旭林, 李捷鹏, 张海仓, 于春功, 王超, 卜东波. 利用深度学习辅助算法设计——以排课问题与旅行商问题为例. 计算机研究与发展, 2026 , 63 (7) : 1670 -1689 . DOI: 10.7544/issn1000-1239.202660017
Jingyan Sui, Shizhe Ding, Boyang Xia, Ruizhi Liu, Zhenxin Ding, Liming Xu, Rui Wang, Xulin Huang, Jiepeng Li, Haicang Zhang, Chungong Yu, Chao Wang, Dongbo Bu. Using Deep Learning to Assist Algorithm Design—Taking Course Scheduling Problem and Traveling Salesman Problem as Examples[J]. Journal of Computer Research and Development, 2026 , 63 (7) : 1670 -1689 . DOI: 10.7544/issn1000-1239.202660017
Year 2026 volume 63 Issue 7
97
43
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202660017
  • Receive Date:2026-01-05
  • Online Date:2026-11-17
  • Published:2026-07-01
Article Data
Affiliations
History
  • Received:2026-01-05
  • Revised:2026-05-28
Affiliations
    1School of Artificial Intelligence and Computer Science, Liaocheng University, Liaocheng, Shandong 252000
    2State Key Lab of Processors (Institute of Computing, Chinese Academy of Sciences), Beijing 100190
    3University of Chinese Academy of Sciences, Beijing 100049
    4Central China Artificial Intelligence Research Institute, Zhengzhou 450046
    5Hangzhou Institute for Advanced Study, UCAS, Hangzhou 310024
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202660017
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT