Page 271 - 《软件学报》2026年第5期

2150 软件学报 2026 年第 37 卷第 5 期

[22] Thornton C, Hutter F, Hoos HH, Leyton-Brown K. Auto-WEKA: Combined selection and hyperparameter optimization of classification
algorithms. In: Proc. of the 19th ACM SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining. Chicago: ACM, 2013. 847–855.
[doi: 10.1145/2487575.2487629]
[23] Kotthoff L, Thornton C, Hoos HH, Hutter F, Leyton-Brown K. Auto-WEKA 2.0: Automatic model selection and hyperparameter
optimization in WEKA. The Journal of Machine Learning Research, 2017, 18(1): 826–830.
[24] Li Y, Jiang J, Gao J, Shao Y, Zhang C, Cui B. Efficient automatic CASH via rising bandits. In: Proc. of the 34th AAAI Conf. on Artificial
Intelligence. New York: AAAI Press, 2020. 4763–4771. [doi: 10.1609/aaai.v34i04.5910]
[25] Shen Y, Lu YP, Li Y, Tu YF, Zhang WT, Cui B. DivBO: Diversity-aware CASH for ensemble learning. In: Proc. of the 36th Int’l Conf.
on Neural Information Processing Systems. New Orleans: ACM, 2022. 2958–2971.
[26] Wang CN, Wang HZ, Mu TY, Li JZ, Gao H. Auto-model: Utilizing research papers and HPO techniques to deal with the CASH problem.
In: Proc. of the 36th IEEE Int’l Conf. on Data Engineering (ICDE). Dallas: IEEE, 2020. 1906–1909. [doi: 10.1109/ICDE48307.2020.
00200]
[27] Zhang XY, Wu H, Chang Z, Jin SW, Tan J, Li FF, Zhang TY, Cui B. ResTune: Resource oriented tuning boosted by meta-learning for
cloud databases. In: Proc. of the 2021 Int’l Conf. on Management of Data. ACM, 2021. 2102–2114. [doi: 10.1145/3448016.3457291]
[28] Cheng DZ, Rao J, Guo YF, Jiang CJ, Zhou XB. Improving performance of heterogeneous mapreduce clusters with adaptive task tuning.
IEEE Trans. on Parallel and Distributed Systems, 2017, 28(3): 774–786. [doi: 10.1109/TPDS.2016.2594765]
[29] Bodin B, Nardi L, Zia MZ, Wagstaff H, Shenoy GS, Emani M, Mawer J, Kotselidis C, Nisbet A, Lujan M, Franke B, Kelly PHJ, O’Boyle
M. Integrating algorithmic parameters into benchmarking and design space exploration in 3D scene understanding. In: Proc. of the 2016
Int’l Conf. on Parallel Architecture and Compilation Techniques. Haifa: IEEE, 2016. 57–69. [doi: 10.1145/2967938.2967963]
[30] Jamshidi P, Velez M, Kästner C, Siegmund N. Learning to sample: Exploiting similarities across environments to learn performance
models for configurable systems. In: Proc. of the 26th ACM Joint Meeting on European Software Engineering Conf. and Symp. on the
Foundations of Software Engineering. Lake Buena Vista: ACM, 2018. 71–82. [doi: 10.1145/3236024.3236074]
[31] Tighineanu P, Skubch K, Baireuther P, Reiss A, Berkenkamp F, Vinogradska J. Transfer learning with Gaussian processes for Bayesian
optimization. In: Proc. of the 25th Int’l Conf. on Artificial Intelligence and Statistics. PMLR, 2022. 6152–6181.
[32] Akaike H. Fitting autoregreesive models for prediction. In: Parzen E, Tanabe K, Kitagawa G, eds. Selected Papers of Hirotugu Akaike.
New York: Springer, 1998. 131–135. [doi: 10.1007/978-1-4612-1694-0_10]
[33] Schwarz G. Estimating the dimension of a model. The Annals of Statistics, 1978, 6(2): 461–464.
[34] Ding J, Tarokh V, Yang YH. Bridging AIC and BIC: A new criterion for autoregression. IEEE Trans. on Information Theory, 2018,
64(6): 4024–4043. [doi: 10.1109/TIT.2017.2717599]
[35] Rosenbaum PR, Rubin DB. The central role of the propensity score in observational studies for causal effects. Biometrika, 1983, 70(1):
41–55. [doi: 10.1093/biomet/70.1.41]
[36] Phind. Phind/Phind-CodeLlama-34B-v2. 2023. https://huggingface.co/Phind/Phind-CodeLlama-34B-v2
[37] Holtzman A, Buys J, Du L, Forbes M, Choi Y. The curious case of neural text degeneration. In: Proc. of the 8th Int’l Conf. on Learning
Representations. Addis Ababa: OpenReview.net, 2020.
[38] Fan A, Lewis M, Dauphin Y. Hierarchical neural story generation. In: Proc. of the 56th Annual Meeting of the Association for
Computational Linguistics. Melbourne: ACL, 2018. 889–898. [doi: 10.18653/v1/P18-1082]
[39] Together AI. The AI acceleration cloud—Fast inference, fine-tuning & training. 2025. https://www.together.ai/
[40] Lu S, Guo DY, Ren S, Huang JJ, Svyatkovskiy A, Blanco A, Clement C, Drain D, Jiang DX, Tang DY, Li G, Zhou LD, Shou LJ, Zhou L,
Tufano M, Gong M, Zhou M, Duan N, Sundaresan N, Deng SK, Fu SY, Liu SJ. CodeXGLUE: A machine learning benchmark dataset for
code understanding and generation. arXiv:2102.04664, 2021.
[41] Lemieux C, Inala JP, Lahiri SK, Sen S. CodaMosa: Escaping coverage plateaus in test generation with pre-trained large language models.
In: Proc. of the 45th IEEE/ACM Int’l Conf. on Software Engineering (ICSE). Melbourne: IEEE, 2023. 919–931. [doi: 10.1109/ICSE
48619.2023.00085]

附中文参考文献
[5] 杨泽洲, 陈思榕, 高翠芸, 李振昊, 李戈, 吕荣聪. 基于深度学习的代码生成方法研究进展. 软件学报, 2024, 35(2): 604–628. http://www.
jos.org.cn/1000-9825/6981.htm [doi: 10.13328/j.cnki.jos.006981]

作者简介
曲慕子, 博士生, CCF 学生会员, 主要研究领域为软件工程.
亢良伊, 博士, 助理研究员, CCF 专业会员, 主要研究领域为智能软件工程, 自然语言处理应用.
刘杰, 博士, 研究员, 博士生导师, CCF 专业会员, 主要研究领域为软件工程, 系统软件, 机器学习.
王帅, 博士, 高级工程师, 主要研究领域为大数据分析处理, 人工智能, 系统集成.
叶丹, 博士, 研究员, 博士生导师, 主要研究领域为网络分布式系统, 软件工程.
黄涛, 博士, 研究员, 博士生导师, CCF 高级会员, 主要研究领域为网络分布式计算, 软件工程.