计算机科学 ›› 2021, Vol. 48 ›› Issue (5): 45-50.doi: 10.11896/jsjkx.201000107

• 计算机软件* 上一篇    下一篇

数据驱动的开源贡献度量化评估与持续优化方法

范家宽1, 王皓月1, 赵生宇2, 周添一1, 王伟1   

  1. 1 华东师范大学数据科学与工程学院 上海200062
    2 同济大学电子与信息工程学院 上海201804
  • 收稿日期:2020-10-19 修回日期:2021-03-10 出版日期:2021-05-15 发布日期:2021-05-09
  • 通讯作者: 王伟(wwang@dase.ecnu.edu.cn)

Data-driven Methods for Quantitative Assessment and Enhancement of Open Source Contributions

FAN Jia-kuan1, WANG Hao-yue1, ZHAO Sheng-yu2, ZHOU Tian-yi1, WANG Wei1   

  1. 1 School of Data Science and Engineering,East China Normal University,Shanghai 200062,China
    2 College of Electronical and Information Engineering,Tongji University,Shanghai 201804,China
  • Received:2020-10-19 Revised:2021-03-10 Online:2021-05-15 Published:2021-05-09
  • About author:FAN Jia-kuan,born in 1995,master.His main research interests include reinforcement learning and multi agent reinforcement learning.(jkfan@stu.ecnu.edu.cn)
    WANG Wei,born in 1979,professor,Ph.D,is a member of China Computer Federation.His main research interests include computational education and open source digital platform.

摘要: 在当今数字化时代,开源技术、开源软件和开源社区日益重要,而通过量化分析方法研究开源领域的问题也已经成为一个重要的趋势。开发者是开源项目中的核心,其贡献度的量化以及量化后的贡献度提升策略,是开源项目能够健康发展的关键。文中提出了一种数据驱动的开源贡献度量化评估与持续优化方法,并通过一个实际的工具框架Rosstor(Robotic Open Source Software Mentor)进行了实现。该框架包含两个主要部分:1)贡献度评估模型,采取了熵权法,可以动态客观地评估开发者的贡献度;2)贡献度持续优化模型,采取了深度强化学习方法,最大化了开发者的贡献度。文中选取了GitHub上若干著名的开源项目的贡献者数据,通过大量且充分的实验验证了Rosstor不仅能够使所有项目上开发者的贡献度得到大幅度提升,而且还具有一定的抗干扰性,充分证明了所提方法和框架的有效性。Rosstor框架为当下广泛开展的开源项目和开源社区的可持续健康发展提供了方法和工具方面的支持。

关键词: 贡献度测量, 贡献增强, 开源软件, 模仿学习, 深度强化学习

Abstract: In recent years,open source technologies,open source software and open source communities have become increasingly significant in digital era,and it has become an important trend to study the open source field through quantitative analysis me-thods.Developers are the core of open source projects,and the quantification of their contributions and the strategies to improve their contributions after quantification are the key to the healthy development of open source projects.We propose a data-driven method for quantitative assessment and continuous optimization of open source contributions.Then,we implement it through a practical framework,Rosstor (Robotic Open Source Software Mentor).The framework consists of two main parts.One is a contribution evaluation model,it adopts an entropy-weight approach and can dynamically and objectively evaluate developers' contributions.Another is a model to enhance contributions,it adopts a deep reinforcement learning approach and can maximize develo-pers' contributions.Contributors' data from a number of famous open source projects on GitHub are selected,and through massive and sufficient experiments,it verifies that Rosstor not only makes the developers' contributions on all projects to be greatly improved,but also has a certain degree of immunity,which fully proves the effectiveness of the framework.The Rosstor framework provides methodological and instrumental support for the sustainable health of open source projects and the open source community.

Key words: Contribution enhancement, Contribution measurement, Deep reinforcement learning, Imitation learning, Open source software

中图分类号: 

  • TP391
[1]XUAN Q,GHAREHYAZIE M,DEVANBU P T,et al.Measu-ring the effect of social communications on individual working rhythms:A case study of open source software[C]// 2012 International Conference on Social Informatics.2012:78-85.
[2]SOWE S K,STAMELOS I,ANGELIS L.Understanding know-ledge sharing activities in free/open source software projects:An empirical study[J].Journal of Systems and Software,2008,3(81):431-446.
[3]BACHMAN N,BERNSTEIN A.When process data quality affects the number of bugs:Correlations in software engineering datasets[C]//2010 7th IEEE Working Conference on Mining Software Repositories (MSR 2010).2010:62-71.
[4]GOURLEY B A,DEVANBU P.Detecting patch submission and acceptance in oss projects[C]//Fourth International Workshop on Mining Software Repositories (MSR'07).ICSE,2007:26.
[5]HO J,ERMON S.Generative adversarial imitation learning[C]//Advances in Neural Information Processing Systems.2016:4565-4573.
[6]BOEH M,LI G H.Value-based software engineering:a casestudy[J].Computer,2003,36(3):33-41.
[7]MARLOW J,DABBISH L,HERBSLEB J.Impression formation in online peer production:Activity traces and personal profiles in github[C]//Proceedings of the 2013 Conference on Computer Supported Cooperative Work(CSCW '13).New York,NY,USA,2013:117-128.
[8]TSAY J,DABBISH L,HERBSLEB J.Influence of social andtechnical factors for evaluating contribution in github[C]//Proceedings of the 36th International Conference on Software Engineering(ICSE 2014).New York,NY,USA,2014:356-366.
[9]X-lab.Github's digital annual report for 2019[OL].https://github.com/X-lab2017/github-analysis-report-2019,2020.
[10]YE D,LIU Z,SUN M,et al.Mastering Complex Control inMOBA Games with Deep Reinforcement Learning[C]//AAAI.2020:6672-6679.
[11]JIANG N,JIN S,DUAN Z,et al.RL-Duet:Online Music Accompaniment Generation Using Deep Reinforcement Learning[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:710-718.
[12]JING M,MA X,HUANG W,et al.Reinforcement Learningfrom Imperfect Demonstrations under Soft Expert Guidance[C]//AAAI.2020:5109-5116.
[13]LILLICRAP T P,HUNT J J,PRITZEL A,et al.Continuouscontrol with deep reinforcement learning[J].arXiv:1509.02971,2015.
[14]JENSE N,SCACCHI W.Role migration and advancement pro-cesses in ossd projects:A comparative case study[C]//29th International Conference on Software Engineering (ICSE'07).2007:364-374.
[15]SCHULMAN J,WOLSKI F,DHARIWAL P,et al.Proximalpolicy optimization algorithms[J].arXiv:1707.06347,2017.
[16]THUNG T F,BISSYANDE ,LO D,et al.Network structure of social coding in github[C]//17th European Conference on Software Maintenance and Reengineering.2013:323-326.
[17]GOUSIOS G,KALLIAMVAKOU E,SPINELLIS D.Measuring developer contribution from software repository data[C]//Proceedings of the 2008 International Working Conference on Mi-ning Software Repositories(MSR '08).New York,NY,USA,2008:129-132.
[18]ZHOU M,MOCKUS A.Who will stay in the floss community? modeling participant's initial behavior[J].IEEE Transactions on Software Engineering,2015,41(1):82-99.
[1] 熊丽琴, 曹雷, 赖俊, 陈希亮.
基于值分解的多智能体深度强化学习综述
Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization
计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[2] 于滨, 李学华, 潘春雨, 李娜.
基于深度强化学习的边云协同资源分配算法
Edge-Cloud Collaborative Resource Allocation Algorithm Based on Deep Reinforcement Learning
计算机科学, 2022, 49(7): 248-253. https://doi.org/10.11896/jsjkx.210400219
[3] 李梦菲, 毛莺池, 屠子健, 王瑄, 徐淑芳.
基于深度确定性策略梯度的服务器可靠性任务卸载策略
Server-reliability Task Offloading Strategy Based on Deep Deterministic Policy Gradient
计算机科学, 2022, 49(7): 271-279. https://doi.org/10.11896/jsjkx.210600040
[4] 谢万城, 李斌, 代玥玥.
空中智能反射面辅助边缘计算中基于PPO的任务卸载方案
PPO Based Task Offloading Scheme in Aerial Reconfigurable Intelligent Surface-assisted Edge Computing
计算机科学, 2022, 49(6): 3-11. https://doi.org/10.11896/jsjkx.220100249
[5] 洪志理, 赖俊, 曹雷, 陈希亮, 徐志雄.
基于遗憾探索的竞争网络强化学习智能推荐方法研究
Study on Intelligent Recommendation Method of Dueling Network Reinforcement Learning Based on Regret Exploration
计算机科学, 2022, 49(6): 149-157. https://doi.org/10.11896/jsjkx.210600226
[6] 李鹏, 易修文, 齐德康, 段哲文, 李天瑞.
一种基于深度学习的供热策略优化方法
Heating Strategy Optimization Method Based on Deep Learning
计算机科学, 2022, 49(4): 263-268. https://doi.org/10.11896/jsjkx.210300155
[7] 欧阳卓, 周思源, 吕勇, 谭国平, 张悦, 项亮亮.
基于深度强化学习的无信号灯交叉路口车辆控制
DRL-based Vehicle Control Strategy for Signal-free Intersections
计算机科学, 2022, 49(3): 46-51. https://doi.org/10.11896/jsjkx.210700010
[8] 代珊珊, 刘全.
基于动作约束深度强化学习的安全自动驾驶方法
Action Constrained Deep Reinforcement Learning Based Safe Automatic Driving Method
计算机科学, 2021, 48(9): 235-243. https://doi.org/10.11896/jsjkx.201000084
[9] 成昭炜, 沈航, 汪悦, 王敏, 白光伟.
基于深度强化学习的无人机辅助弹性视频多播机制
Deep Reinforcement Learning Based UAV Assisted SVC Video Multicast
计算机科学, 2021, 48(9): 271-277. https://doi.org/10.11896/jsjkx.201000078
[10] 梁俊斌, 张海涵, 蒋婵, 王天舒.
移动边缘计算中基于深度强化学习的任务卸载研究进展
Research Progress of Task Offloading Based on Deep Reinforcement Learning in Mobile Edge Computing
计算机科学, 2021, 48(7): 316-323. https://doi.org/10.11896/jsjkx.200800095
[11] 王英恺, 王青山.
能量收集无线通信系统中基于强化学习的能量分配策略
Reinforcement Learning Based Energy Allocation Strategy for Multi-access Wireless Communications with Energy Harvesting
计算机科学, 2021, 48(7): 333-339. https://doi.org/10.11896/jsjkx.201100154
[12] 周仕承, 刘京菊, 钟晓峰, 卢灿举.
基于深度强化学习的智能化渗透测试路径发现
Intelligent Penetration Testing Path Discovery Based on Deep Reinforcement Learning
计算机科学, 2021, 48(7): 40-46. https://doi.org/10.11896/jsjkx.210400057
[13] 李贝贝, 宋佳芮, 杜卿芸, 何俊江.
DRL-IDS:基于深度强化学习的工业物联网入侵检测系统
DRL-IDS:Deep Reinforcement Learning Based Intrusion Detection System for Industrial Internet of Things
计算机科学, 2021, 48(7): 47-54. https://doi.org/10.11896/jsjkx.210400021
[14] 范艳芳, 袁爽, 蔡英, 陈若愚.
车载边缘计算中基于深度强化学习的协同计算卸载方案
Deep Reinforcement Learning-based Collaborative Computation Offloading Scheme in VehicularEdge Computing
计算机科学, 2021, 48(5): 270-276. https://doi.org/10.11896/jsjkx.201000005
[15] 黄志勇, 吴昊霖, 王壮, 李辉.
基于平均神经网络参数的DQN算法
DQN Algorithm Based on Averaged Neural Network Parameters
计算机科学, 2021, 48(4): 223-228. https://doi.org/10.11896/jsjkx.200600177
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!