计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11): 320-329.doi: 10.11896/jsjkx.241200129

• 计算机软件 • 上一篇    下一篇

MDGRec:基于多元关系融合的移动应用第三方库推荐方法

陈煜涵, 王健, 李段腾川, 郑超, 李兵   

  1. 武汉大学计算机学院 武汉 430072
  • 收稿日期:2024-12-17 修回日期:2025-03-24 出版日期:2025-11-15 发布日期:2025-11-06
  • 通讯作者: 李兵(bingli@whu.edu.cn)
  • 作者简介:(lctaba@whu.edu.cn)
  • 基金资助:
    国家自然科学基金重点项目(62032016)

MDGRec:Multi-relation Aware Third-party Library Recommendation with Dual Graph NeuralNetworks for Mobile Application Development

CHEN Yuhan, WANG Jian, LI Duantengchuan, ZHENG Chao, LI Bing   

  1. School of Computer Science,Wuhan University,Wuhan 430072,China
  • Received:2024-12-17 Revised:2025-03-24 Online:2025-11-15 Published:2025-11-06
  • About author:CHEN Yuhan,born in 1999,postgra-duate.His main research interests include recommender systems,software engineering and service computing.
    LI Bing,born in 1969,Ph.D,professor,Ph.D supervisor,is a distinguished member of CCF(No.06539D).His main research interests include software engineering,service computing and artificial intelligence.
  • Supported by:
    Key Program of the National Natural Science Foundation of China(62032016).

PDF (PC)

22

摘要： 第三方库推荐系统旨在向开发者推荐合适的第三方库,以提高移动应用的开发效率。然而,现有的基于图神经网络的方法大多在一个异构交互图中同时传播移动应用和第三方库的节点信息,存在数据不平衡和特征混淆的问题。此外,现有方法忽视了第三方库推荐场景关系的复杂性,限制了推荐准确性。为此,提出了一种基于多元关系融合的移动应用第三方库推荐方法。模型使用双图结构分别对移动应用和第三方库进行建模,生成相应的嵌入向量。在此基础上,模型融合了第三方库推荐场景中的多元关系,在不同关系维度上传播节点信息,并使用自适应权重刻画不同关系在信息传播中的贡献,以生成细粒度的节点特征。在两个真实世界数据集上的实验结果表明,所提方法在各项指标上优于主流的基线模型。

关键词: 推荐系统, 图神经网络, 多元关系, 第三方库, 移动应用

Abstract: Third-party library(TPL)recommendation systems are designed to help developers select suitable libraries,thus improving the efficiency of mobile application(App) development.Most existing methods based on graph neural networks typically propagate information for both App and TPL nodes within a single heterogeneous interaction graph,leading to issues of data imbalance and feature confusion,limiting the recommendation accuracy.Moreover,these methods often fail to account for the complex relationships inherent in the context of TPL recommendation.To overcome these limitations,this paper proposes a multi-relation aware third-party library recommendation method with dual graph neural networks for mobile application development(MDGRec).The model employs a dual graph structure to separately model Apps and TPLs,generating distinct embeddings.Based on this,the model incorporates multiple relationships and uses adaptive weights to capture the contribution of each relation in information propagation,constructing fine-grained node representations.Experimental results on two real-world datasets show that the proposed model surpasses mainstream baselines across all metrics.

Key words: Recommender systems, Graph neural network, Multi-relation, Third-party library, Mobile application

中图分类号: 

  • TP311
[1]LI M H,WANG W,WANG P,et al.Libd:Scalable and precise third-party library detection in android markets[C]//2017 IEEE/ACM 39th International Conference on Software Engineering(ICSE).New York:IEEE,2017:335-346.
[2]BACKES M,BUGIEL S,DERR E.Reliable third-party library detection in android and its security applications[C]//Procee-dings of the 2016 ACM SIGSAC Conference on Computer and Communications Security.New York:ACM,2016:356-367.
[3]ZHAN X,LIU T M,FAN L L,et al.Research on third-party libraries in android apps:A taxonomy and systematic literature review[J].IEEE Transactions on Software Engineering,2021,48(10):4181-4213.
[4]ZHANG Y H,WANG J C,HUANG H X,et al.Understanding and conquering the difficulties in identifying third-party libraries from millions of android apps[J].IEEE Transactions on Big Data,2021,8(6):1511-1523.
[5]NGUYEN P T,DI ROCCO J,DI RUSCIO D,et al.CrossRec:Supporting software developers by recommending third-party libraries[J].Journal of Systems and Software,2020,161:110460.
[6]SALZA P,PALOMBA F,DI NUCCI D,et al.Third-party li-braries in mobile apps:When,how,and why developers update them[J].Empirical Software Engineering,2020,25:2341-2377.
[7]HENRIQUES H,LOURENÇO H,AMARAL V,et al.Improving the developer experience with a low-code process modelling language[C]//Proceedings of the 21th ACM/IEEE InternationalConference on Model Driven Engineering Languages and Systems.New York:ACM,2018:200-210.
[8]THUNG F,LO D,LAWALL J.Automated library recommendation[C]//2013 20th Working Conference on Reverse Engineering(WCRE).New York:IEEE,2013:182-191.
[9]ZHAO X Q,LI S P,YU H,et al.Accurate library recommendation using combining collaborative filtering and topic model for mobile development[J].IEICE Transactions on Information and Systems,2019,102(3):522-536.
[10]LI B,HE Q,CHEN F F,et al.Embedding app-library graph for neural third party library recommendation[C]//Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering.New York:ACM,2021:466-477.
[11]JIN Y,ZHANG Y,ZHANG Y W.Neighbor Library-AwareGraph Neural Network for Third Party Library Recommendation[J].Tsinghua Science and Technology,2023,28(4):769-785.
[12]HE Q,LI B,CHEN F F,et al.Diversified third-party library prediction for mobile app development[J].IEEE Transactions on Software Engineering,2020,48(1):150-165.
[13]YU H,XIA X,ZHAO X Q,et al.Combining collaborative filtering and topic modeling for more accurate android mobile app library recommendation[C]//Proceedings of the 9th Asia-Pacific Symposium on Internetware.New York:ACM,2017:1-6.
[14]OUNI A,KULA R G,KESSENTINI M,et al.Search-basedsoftware library recommendation using multi-objective optimization[J].Information and Software Technology,2017,83:55-75.
[15]WANG X,HE X N,WANG M,et al.Neural graph collaborative filtering[C]//Proceedings of the 42nd international ACM SIGIR Conference on Research and Development in Information Retrieval.New York:ACM,2019:165-174.
[16]ZOU C M,FAN Z F.GELIBREC:Third-Party Libraries Recommendation Using Graph Neural Network[C]//International Conference on Database Systems for Advanced Applications.Cham:Springer,2022:332-340.
[17]SU J,ZHAO T,WU J,et al.Graph Convolution Recommendation Algorithm Integrating Multi-relationship Preferences[C]//International Conference on Intelligent Computing.Singapore:Springer,2024:167-177.
[18]CHEN H,HE J,XU W,et al.Enhanced multi-relationships integration graph convolutional network for inferring substitutable and complementary items[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Palo Alto,CA:AAAI,2023:4157-4165.
[19]SCHAFER J B,FRANKOWSKI D,HERLOCKER J,et al.Collaborative filtering recommender systems[M]//The Adaptive Web:Methods and Strategies of Web Personalization.Berlin:Springer,2007:291-324.
[20]HE X N,LIAO L Z,ZHANG H W,et al.Neural collaborative filtering[C]//Proceedings of the 26th International Conference on World Wide Web.New York:ACM,2017:173-182.
[21]REN Q,LI B,WANG J,et al.Hybrid Recommendation Method of Third-party Library for Mobile Application Development[J].Journal of Chinese Mini-Micro Computer Systems,2019,40(9):1809-1814.
[22]KOREN Y,BELL R,VOLINSKY C.Matrix factorization techniques for recommender systems[J].Computer,2009,42(8):30-37.
[23]RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:Bayesian personalized ranking from implicit feedback[J].arXiv:1205.2618,2012.
[24]FU S H,LIU W F,ZHANG K,et al.Semi-supervised classification by graph p-Laplacian convolutional networks[J].Information Sciences,2021,560:92-106.
[25]WU F,SOUZA A,ZHANG T Y,et al.Simplifying graph convolutional networks[C]//International Conference on Machine Learning.New York:PMLR,2019:6861-6871.
[26]MAO K L,ZHU J M,XIAO X,et al.UltraGCN:ultra simplification of graph convolutional networks for recommendation[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.New York:ACM,2021:1253-1262.
[27]FAN W Q,MA Y,LI Q,et al.Graph neural networks for social recommendation[C]//The World Wide Web Conference.New York:ACM,2019:417-426.
[28]HE X N,DENG K,WANG X,et al.Lightgcn:Simplifying and powering graph convolution network for recommendation[C]//Proceedings of the 43rd International ACM SIGIR conference on research and development in Information Retrieval.New York:ACM,2020:639-648.
[29]ZHAO J,ZHANG X,GAO C,et al.KG2Lib:knowledge-graph-based convolutional network for third-party library recommendation[J].The Journal of Supercomputing,2023,79(1):1-26.
[30]LI B,QUAN H,WANG J,et al.Neural Library Recommendation by Embedding Project-Library Knowledge Graph[J].IEEE Transactions on Software Engineering,2024,50(6):1620-1638.
[31]ZHOU L,CHEN W Y,ZENG D Y,et al.DPGNN:Dual-perception graph neural network for representation learning[J].Knowledge-Based Systems,2023,268:110377.
[32]LIU M,GAO H Y,JI S W.Towards deeper graph neural networks[C]//Proceedings of the 26th ACM SIGKDD InternationalConference on Knowledge Discovery & Data Mining.New York:ACM,2020:338-348.
[33]LI X,FU C F,ZHAO Z Y,et al.Dual-Channel Multiplex Graph Neural Networks for Recommendation[J].arXiv:2403.11624,2024.
[34]ZHANG R Y,MA H F,LI Q F,et al.Dual-view self-supervised co-training for knowledge graph recommendation[C]//International Conference on Database Systems for Advanced Applications.Cham:Springer,2023:113-128.
[35]ZHUANG C Y,MA Q.Dual graph convolutional networks for graph-based semi-supervised classification[C]//Proceedings of the 2018 World Wide Web Conference.New York:ACM,2018:499-508.
[36]ZHANG Y,ZHANG Y W,ZHAO Y C,et al.Dual Variational Graph Reconstruction Learning for Social Recommendation[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(11):6002-6015.
[37]LUO H,MENG X,WANG S,et al.Spectral-Based Graph Neural Networks for Complementary Item Recommendation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.AAAI,2024:8868-8876.
[38]WU B,ZHONG L H,LI H,et al.Efficient complementary graphconvolutional network without negative sampling for item re-commendation[J].Knowledge-Based Systems,2022,256:109758.
[39]LI D T C,GAO Y X,WANG Z H,et al.Homogeneous graph neural networks for third-party library recommendation[J].Information Processing & Management,2024,61(6):103831.
[40]NGUYEN P T,RUBEI R,DI ROCCO J,et al.Dealing withPopularity Bias in Recommender Systems for Third-party Libraries:How far Are We?[C]//2023 IEEE/ACM 20th International Conference on Mining Software Repositories(MSR).New York:IEEE,2023:12-24.
[41]KINGMA D P.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.
[42]GLOROT X,BENGIO Y.Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics.New York:JMLR,2010:249-256.
[43]RONG Y,HUANG W B,XU T Y,et al.Dropedge:Towardsdeep graph convolutional networks on node classification[J].arXiv:1907.10903,2019.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发