开源协同结构建模与多层网络链路预测方法

doi:10.3969/j.issn.1000-5641.2025.05.011

华东师范大学学报（自然科学版） ›› 2025, Vol. 2025 ›› Issue (5): 109-124.doi: 10.3969/j.issn.1000-5641.2025.05.011

• 开源生态发展与治理 • 上一篇

开源协同结构建模与多层网络链路预测方法

赵普¹(), 彭庆喜¹^,*(), 张雨昂², 金协杰¹, 赵德洲³

1. 武汉学院信息工程学院, 武汉　430210
2. 中国地质大学(武汉) 地理与信息工程学院, 武汉　430078
3. 枣庄技师学院基础教学部, 山东枣庄　277000

收稿日期:2025-06-27 接受日期:2025-07-31 出版日期:2025-09-25 发布日期:2025-09-25
通讯作者: 彭庆喜 E-mail:zhaopu_2025@qq.com;695979317@qq.com
作者简介:赵　普, 男, 硕士, 助教, 研究方向为复杂网络、开源生态分析. E-mail: zhaopu_2025@qq.com
基金资助:
湖北省高校优秀中青年科技创新团队 (T2022055); 湖北一丹大学教育发展基金会科研基金 (JJA202509); 湖北省教育厅科学研究计划指导性项目 (B2024360)

Open-source collaboration structure modeling and multilayer-network link-prediction methods

Pu ZHAO¹(), Qingxi PENG¹^,*(), Yuang ZHANG², Xiejie JIN¹, Dezhou ZHAO³

1. School of Information Engineering, Wuhan College, Wuhan　430210, China
2. School of Geography and Information Engineering, China University of Geosciences, Wuhan　430078, China
3. Ministry of Basic Education, Zaozhuang Technician College, Zaozhuang, Shandong　277000, China

Received:2025-06-27 Accepted:2025-07-31 Online:2025-09-25 Published:2025-09-25
Contact: Qingxi PENG E-mail:zhaopu_2025@qq.com;695979317@qq.com

摘要/Abstract

摘要：

开源生态中项目间协同关系日益复杂, 涵盖依赖共现、语言一致与开发者共享等多维复用机制. 传统图模型难以统一表达此类异构结构, 限制了对潜在协作关系的识别能力. 面向开源场景, 提出了一种基于多层图结构建模与结构融合链路预测方法相结合的分析框架. 通过构建包含3类协同层的无权多层网络, 并设计结构重合度调节与社群差异性评分机制, 来增强模型的结构感知与语义解释能力. 实验结果表明, 该方法在多个真实数据集上均优于现有主流链路预测算法, 尤其在结构异质性强的开源网络中表现显著. 进一步分析显示, 模型预测结果具备良好的社群一致性与语义可还原性. 研究表明, 该方法能够有效识别开源项目间潜在协同路径, 并为复用结构建模与社群分析提供结构性支撑.

关键词: 开源协同网络, 多层网络建模, 链路预测, 社群识别

Abstract:

Collaborative relationships among open-source projects are becoming increasingly complex, involving multiple reuse mechanisms such as dependency co-usage, language consistency, and contributor overlap. Traditional graph models struggle to represent these heterogeneous structures in a unified manner, limiting their ability to identify potential collaboration links. This paper proposes an analytical framework that integrates multilayer graph modeling with structure-aware link prediction, tailored to open-source ecosystems. A three-layer unweighted graph is constructed to capture different types of collaborations, and two structural enhancements—layer overlap modulation and community-aware scoring—are introduced to improve structural perception and semantic interpretability. Experimental results on multiple real-world datasets show that the proposed method consistently outperforms mainstream link prediction algorithms, particularly in networks with high structural heterogeneity. Further analysis reveals that the predicted links exhibit strong community consistency and semantic recoverability. Overall, the proposed approach effectively uncovers latent collaboration paths among open-source projects and provides structural support for reuse modeling and community evolution analysis.

Key words: open-source collaboration network, multilayer network modeling, link prediction, community detection

中图分类号:

TP311.5

赵普, 彭庆喜, 张雨昂, 金协杰, 赵德洲. 开源协同结构建模与多层网络链路预测方法[J]. 华东师范大学学报（自然科学版）, 2025, 2025(5): 109-124.

Pu ZHAO, Qingxi PENG, Yuang ZHANG, Xiejie JIN, Dezhou ZHAO. Open-source collaboration structure modeling and multilayer-network link-prediction methods[J]. J* E* C* N* U* N* S*, 2025, 2025(5): 109-124.

图/表 12

图1

图2

表1

图3

图4

图5

图6

图7

表2

表3

表4

表5

参考文献 37

1	MARTÍNEZ V, BERZAL F, CUBERO J C.. A survey of link prediction in complex networks. ACM Computing Surveys, 2017, 49 (4): 1- 33.
2	WANG X, JI H Y, SHI C, et al. Heterogeneous graph attention network [C]// The World Wide Web Conference. ACM, 2019: 2022-2032.
3	NAJARI S, SALEHI M, RANJBAR V, et al.. Link prediction in multiplex networks based on interlayer similarity. Physica A: Statistical Mechanics and Its Applications, 2019, 536, 120978.
4	FU X Y, ZHANG J N, MENG Z Q, et al. MAGNN: Metapath aggregated graph neural network for heterogeneous graph embedding [C]// Proceedings of The Web Conference 2020. ACM, 2020: 2331-2341.
5	XIONG H, YAN J C, PAN L. Contrastive multi-view multiplex network embedding with applications to robust network alignment [C]// Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. ACM, 2021: 1913-1923.
6	MISHRA S, SINGH S S, KUMAR A, et al. HOPLP − MUL: Link prediction in multiplex networks based on higher order paths and layer fusion [J]. Applied Intelligence, 2023, 53(3): 3415-3443.
7	CHAI L, TU L L, WANG X J, et al.. Hypergraph modeling and hypergraph multi-view attention neural network for link prediction. Pattern Recognition, 2024, 149, 110292.
8	ZHAO P, YOU L, WANG M, et al.. Multilayer network link prediction considering multiple correlation features. Expert Systems with Applications, 2025, 285, 127700.
9	LYULINA E, JAHANSHAHI M. Building the collaboration graph of open-source software ecosystem [C]// 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR). IEEE, 2021: 618-620.
10	MORADI-JAMEI B, KRAMER B L, CALDERÓN J B S, et al. Community formation and detection on GitHub collaboration networks [C]// Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. ACM, 2021: 244-251.
11	AGROSKIN A, LYULINA E, TITOV S, et al. Constructing temporal networks of OSS programming language ecosystems [C]// 2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER). IEEE, 2023: 663-667.
12	MATRAGKAS N, WILLIAMS J R, KOLOVOS D S, et al. Analysing the ‘biodiversity’ of open source ecosystems: The GitHub case [C]// Proceedings of the 11th Working Conference on Mining Software Repositories. ACM, 2014: 356-359.
13	林海铭, 田春岐, 王伟. 基于二分网络表示学习的开源项目推荐方法 [J]. 计算机科学与应用, 2022, 12(1): 54-62.
14	ORIOL M, MÜLLER C, MARCO J, et al. Comprehensive assessment of open source software ecosystem health [J]. Internet of Things, 2023, 22: 100808.
15	SUN W J, IWUCHUKWU S, ALI BANGASH A, et al. An empirical study to investigate collaboration among developers in open source software (OSS) [C]// 2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR). IEEE, 2023: 352-356.
16	连薛超, 刘维, 王清帅, 等. 面向高冲突事务处理的架构设计和优化[J]. 华东师范大学学报 (自然科学版), 2023(6): 28-38.
17	XIA X Y, ZHAO S Y, HAN F Y, et al. OpenDigger: Data mining and information service system for open collaboration digital ecosystem [EB/OL]. (2023-11-26)[2025-06-26]. https://arxiv.org/abs/2311.15204.
18	PRANA G A A, SHARMA A, SHAR L K, et al.. Out of sight, out of mind? How vulnerable dependencies affect open-source projects. Empirical Software Engineering, 2021, 26 (4): 59.
19	MONTANDON J E, VALENTE M T, SILVA L L.. Mining the technical roles of GitHub users. Information and Software Technology, 2021, 131, 106485.
20	LI W, MENG N, LI L, et al. Understanding language selection in multi-language software projects on GitHub [C]// 2021 IEEE/ACM 43rd International Conference on Software Engineering: Companion Proceedings (ICSE-Companion). IEEE, 2021: 256-257.
21	ZHANG Y, WU Y W, CHEN T T, et al. How do developers talk about GitHub actions? evidence from online software development community [C]// Proceedings of the IEEE/ACM 46th International Conference on Software Engineering. ACM, 2024: 1-13.
22	蒲秋梅, 席作新, 黄丽蓉, 等. 基于 GitHub 的用户影响力评估算法 [J]. 中南民族大学学报(自然科学版), 2023, 42(5): 672-677.
23	王明宇, 宫庆媛, 瞿晶晶, 等. 基于机器学习的 GitHub 企业影响力分析与预测 [J]. 智能科学与技术学报, 2023, 5(3): 330-342.
24	郑阳, 郑丽伟, 牟永敏. prAMD: 一种 GitHub pull-request 协作机制自动设计方法 [J]. 计算机应用与软件, 2024, 41(9): 9-16.
25	CAO Y L, CHEN L, MA W, et al.. Towards better dependency management: A first look at dependency smells in Python Projects. IEEE Transactions on Software Engineering, 2023, 49 (4): 1741- 1765.
26	DABIC O, AGHAJANI E, BAVOTA G. Sampling projects in GitHub for MSR studies [C]// 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR). IEEE, 2021: 560-564.
27	CALEFATO F, GEROSA M A, IAFFALDANO G, et al.. Will you come back to contribute? Investigating the inactivity of OSS core developers in GitHub. Empirical Software Engineering, 2022, 27 (3): 76.
28	SAROAR S G, NAYEBI M. Developers’ perception of GitHub actions: A survey analysis [C]// Proceedings of the 27th International Conference on Evaluation and Assessment in Software Engineering. ACM, 2023: 121-130.
29	ARRAR D, KAMEL N, LAKHFIF A.. A comprehensive survey of link prediction methods. The Journal of Supercomputing, 2024, 80 (3): 3902- 3942.
30	DANTAS SILVA F S, LIMA M P S, CORUJO D, et al.. A comprehensive step-wise survey of multiple attribute decision-making mobility approaches. IEEE Access, 2024, 12, 108616- 108656.
31	GAO M Z, JIAO P F, LU R L, et al. Inductive link prediction via interactive learning across relations in multiplex networks [J]. IEEE Transactions on Computational Social Systems, 2024, 11(3): 3118-3130.
32	COSCIA M, SZELL M.. Multilayer graph association rules for link prediction. Proceedings of the International AAAI Conference on Web and Social Media, 2021, 15, 129- 139.
33	TANG R, CHEN X S, WEI C C, et al.. Interlayer link prediction based on multiple network structural attributes. Computer Networks, 2022, 203, 108651.
34	JALILI M, OROUSKHANI Y, ASGARI M, et al.. Link prediction in multiplex online social networks. Royal Society Open Science, 2017, 4 (2): 160863.
35	ROZEMBERCZKI B, ALLEN C, SARKAR R.. Multi-Scale attributed node embedding. Journal of Complex Networks, 2021, 9 (2): cnab014.
36	CARRINGTON A M, MANUEL D G, FIEGUTH P W, et al.. Deep ROC analysis and AUC as balanced average accuracy, for improved classifier selection, audit and explanation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (1): 329- 341.
37	YACOUBY R, AXMAN D. Probabilistic extension of precision, recall, and F1 score for more thorough evaluation of classification models [C]// Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems. Stroudsburg, PA, USA: ACL, 2020: 79-91.

Network	Layer	$ \left\|V\right\| $	$ \left\|E\right\| $	$ C $	$ \left\langle{k}\right\rangle $	$ H $
CKM	1	215	449	0.2600	4.1767	1.4941
	2	231	498	0.2598	4.3117	1.3483
	3	228	423	0.2108	3.7105	1.2373
Aarhus	1	60	193	0.6733	6.4333	1.2129
	2	32	124	0.5404	7.7500	1.2268
	3	25	21	0.2680	1.6800	1.3889
	4	47	88	0.3925	3.7447	1.5143
	5	60	194	0.6396	6.4667	1.6652
Vickers	1	29	240	0.7537	16.5517	1.0993
	2	29	126	0.6807	8.6897	1.2750
	3	29	152	0.7128	10.4828	1.2495
TF	1	1564	14090	0.1314	18.0179	3.3864
TF	2	1508	18471	0.3436	24.4973	3.7752
KjwxData	1	21447	68373	0.4712	6.3760	5.7290
	2	44513	121240	0.1980	5.4470	1.1550
	3	12282	22071	0.1856	3.5943	8.8781
OSS-281	1	281	634	0.0195	4.5125	0.2150
	2	281	5561	0.4170	39.5801	0.0187
	3	281	760	0.5001	5.4093	1.1937
SNAP-GitHub	1	200	45	0.0251	0.4537	1.8046

$ \alpha $	$ \beta $	CKM	Aarhus	Vickers	TF	KjwxData	OSS-281	SNAP
0.2	0.8	0.9423	0.9228	0.9391	0.9199	0.9229	0.9286	0.8716
0.4	0.6	0.9505	0.9295	0.9505	0.9217	0.9225	0.9343	0.8719
0.6	0.4	0.951	0.9281	0.9475	0.9254	0.9299	0.9443	0.8787
0.8	0.2	0.9468	0.9269	0.9426	0.9291	0.9308	0.9346	0.8741

$ \alpha $	$ \beta $	CKM	Aarhus	Vickers	TF	KjwxData	OSS-281	SNAP
0.2	0.8	0.3445	0.3104	0.8055	0.4282	0.5296	0.4961	0.4069
0.4	0.6	0.3448	0.3201	0.8075	0.4377	0.5401	0.4973	0.4077
0.6	0.4	0.3469	0.3196	0.8109	0.4361	0.5366	0.5041	0.4093
0.8	0.2	0.3465	0.3141	0.8064	0.4394	0.5328	0.4961	0.4014

Networks	MultiLayer	Merged-SingleLayer	Dev-Contributor Only	Random-Wiring
OSS-281	0.9407	0.9225	0.9142	0.8942
SNAP-GitHub	0.8832	0.8656	0.8487	0.8356
KjwxData	0.9297	0.9199	0.9035	0.8863

Networks	MultiLayer	Merged-SingleLayer	Dev-Contributor Only	Random-Wiring
OSS-281	0.4977	0.4806	0.4644	0.4393
SNAP-GitHub	0.4105	0.3885	0.3708	0.3531
KjwxData	0.5431	0.5203	0.4993	0.4751

开源协同结构建模与多层网络链路预测方法

Open-source collaboration structure modeling and multilayer-network link-prediction methods

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 37

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈宇航, 王世宙, 汤正婷, 陈良育, 姜宁康. 基于代码和描述文本相融合的软件分类研究[J]. 华东师范大学学报（自然科学版）, 2025, 2025(1): 46-58.
[2]	陈杰, 沈文怡, 吴问宇, 毛嘉莉. 面向骑行地图推断的轨迹数据质量提升方法[J]. 华东师范大学学报（自然科学版）, 2023, 2023(6): 14-27.
[3]	郁毅明, 洪语晨, 王晔, 董启文. 化工材料配方的实验数据治理模块设计[J]. 华东师范大学学报（自然科学版）, 2022, 2022(5): 1-13.
[4]	孙晴, 梁冠宇, 武延军, 武斌, 田春岐, 王伟. 数据驱动的开源软件供应链可维护性风险分析方法[J]. 华东师范大学学报（自然科学版）, 2022, 2022(5): 90-99.
[5]	龚鑫, 徐立华, 窦亮, 赵瑞祥. 金融科技软件自动化测试用例的冗余评价和削减方法[J]. 华东师范大学学报（自然科学版）, 2022, 2022(4): 43-55.
[6]	纪宇, 何一璇, 吴国群, 吴敏. 基于Prony-like方法的第一类贝塞尔函数逼近[J]. 华东师范大学学报(自然科学版), 2019, 2019(6): 42-60.
[7]	张涛, 张小磊, 李宇明, 张春熙, 张蓉. Woodpecker+:基于数据特征的自定义负载性能评测[J]. 华东师范大学学报(自然科学版), 2019, 2019(5): 190-202.
[8]	张衡, 陈良育. Levenshtein算法优化及在题库判重中的应用[J]. 华东师范大学学报(自然科学版), 2018, 2018(5): 154-163.
[9]	李捷荧, 李宇明, 张小磊, 张蓉. Woodpecker:支持细粒度冲突模拟的数据库测试框架[J]. 华东师范大学学报(自然科学版), 2018, 2018(2): 77-88.
[10]	杨乐, 柳银萍, 李志斌. Emathema：在线的方程自动求解平台[J]. 华东师范大学学报(自然科学版), 2017, (3): 20-28.
[11]	赵大鹏,梁磊,田秀霞,王晓玲. LBS的隐私保护：模型与进展[J]. 华东师范大学学报(自然科学版), 2015, 2015(5): 28-45.
[12]	韩文文;王玲;陈优广 . 基于亚像素文本图像的分割算法 [J]. 华东师范大学学报(自然科学版), 2007, 2007(3): 100-106.
[13]	顾星晔;王琦;过仲阳;吴健平. 地理数据多边形动态显示的方法研究(简报)[J]. 华东师范大学学报(自然科学版), 2007, 2007(2): 122-125.
[14]	王远飞;陆涛;宓伟杰;朱海燕;邵德民;鲁小琴;冯泾贤. 基于GIS技术的热带气旋信息系统设计与实现(简报)[J]. 华东师范大学学报(自然科学版), 2006, 2006(4): 137-140.
[15]	王远飞;周枫;刘志强;宓伟杰;陆涛;丁金宏. 浦东新区人口普查地理信息系统的设计与实现[J]. 华东师范大学学报(自然科学版), 2006, 2006(2): 27-32.