Neighbor Library-Aware Graph Neural Network for Third Party Library Recommendation

作     者：Ying Jin Yi Zhang Yiwen Zhang Ying Jin;Yi Zhang;Yiwen Zhang

作者机构：School of Artificial Intelligence and Big DataHefei UniversityHefei 230601China School of Computer Science and TechnologyAnhui UniversityHefei 230601China 

出 版 物：《清华大学学报:自然科学版(英文版)》 (Tsinghua Science and Technology)

年 卷 期：2023年第28卷第4期

页      面：769-785页

核心收录：

学科分类：07[理学] 08[工学] 081104[工学-模式识别与智能系统] 070104[理学-应用数学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0503[文学-新闻传播学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported by the Key Project of Nature Science Research for Universities of Anhui Province of China(No.KJ2020A0657) the National Natural Science Foundation of China(Nos.62272001,61872002,and 62276146) the University Collaborative Innovation Project of Anhui Province(No.GXXT-2021-087). 

主　　题：Third-Party Library(TPL) TPL recommendation Graph Neural Network(GNN) bipartite graph 

摘      要：Modern software development has moved toward agile growth and rapid delivery,where developers must meet the changing needs of users instantaneously.In such a situation,plug-and-play Third-Party Libraries(TPLs)introduce a considerable amount of convenience to developers.However,selecting the exact candidate that meets the project requirements from the countless TPLs is challenging for developers.Previous works have considered setting up a personalized recommender system to suggest TPLs for developers.Unfortunately,these approaches rarely consider the complex relationships between applications and TPLs,and are unsatisfactory in accuracy,training speed,and convergence speed.In this paper,we propose a new end-to-end recommendation model called Neighbor Library-Aware Graph Neural Network(NLA-GNN).Unlike previous works,we only initialize one type of node embedding,and construct and update all types of node representations using Graph Neural Networks(GNN).We use a simplified graph convolution operation to alternate the information propagation process to increase the training efficiency and eliminate the heterogeneity of the app-library bipartite graph,thus efficiently modeling the complex high-order relationships between the app and the library.Extensive experiments on large-scale real-world datasets demonstrate that NLA-GNN achieves consistent and remarkable improvements over state-of-the-art baselines for TPL recommendation tasks.