功能互补关系增强的云API推荐方法

doi:10.11959/j.issn.1000-436x.2023093

通信学报 ›› 2023, Vol. 44 ›› Issue (6): 125-137.doi: 10.11959/j.issn.1000-436x.2023093

功能互补关系增强的云API推荐方法

陈真¹^,², 陈文辉¹, 刘啸威¹, 尤殿龙¹^,², 刘林林³, 申利民¹^,²

¹ 燕山大学信息科学与工程学院，河北秦皇岛 066004
² 燕山大学河北省计算机虚拟技术与系统集成重点实验室，河北秦皇岛 066004
³ 中国科学院文献情报中心，北京 100190

修回日期:2023-04-18 出版日期:2023-06-25 发布日期:2023-06-01
作者简介:陈真（1987- ），男，陕西宝鸡人，博士，燕山大学副教授、博士生导师，主要研究方向为服务计算、推荐系统和服务化软件开发等
陈文辉（1997- ），男，山东济宁人，燕山大学硕士生，主要研究方向为服务计算、云API推荐等
刘啸威（2000- ），男，山东枣庄人，燕山大学硕士生，主要研究方向为服务计算、数据挖掘、云API推荐等
尤殿龙（1981- ），男，内蒙古赤峰人，博士，燕山大学副教授，主要研究方向为数据挖掘、特征选择和推荐系统等
刘林林（1990- ），男，山东泰安人，中国科学院文献情报中心馆员，主要研究方向为科技信息处理、知识挖掘和推荐系统等
申利民（1962- ），男，黑龙江佳木斯人，博士，燕山大学教授，主要研究方向为协同计算、服务计算和信息安全等
基金资助:
国家自然科学基金资助项目(62102348);国家自然科学基金资助项目(62276226);河北省自然科学基金资助项目(F2022203012);河北省自然科学基金资助项目(F2021203038);河北省创新能力提升计划基金资助项目(22567626H);河北省研究生创新基金资助项目(CXZZSS2023048)

Functional complementarity relationship enhanced cloud API recommendation method

Zhen CHEN¹^,², Wenhui CHEN¹, Xiaowei LIU¹, Dianlong YOU¹^,², Linlin LIU³, Limin SHEN¹^,²

¹ School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, China
² Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province, Yanshan University, Qinhuangdao 066004, China
³ National Science Library, Chinese Academy of Sciences, Beijing 100190, China

Revised:2023-04-18 Online:2023-06-25 Published:2023-06-01
Supported by:
The National Natural Science Foundation of China(62102348);The National Natural Science Foundation of China(62276226);The Natural Science Foundation of Hebei Province(F2022203012);The Natural Science Foundation of Hebei Province(F2021203038);Innovation Capability Improvement Plan Project of Hebei Province(22567626H);Graduate Innovation Funding Project of Hebei Province(CXZZSS2023048)

摘要/Abstract

摘要：

当前云API推荐方法主要采用相似性计算或者利用Mashup的历史调用来生成推荐结果，忽略了Mashup与云API之间有益的功能互补关系。针对上述问题，提出一种基于功能互补关系增强的云API推荐方法。首先，利用标签共现对功能互补关系进行刻画。然后，计算功能互补得分来刻画云API和Mashup之间的功能互补程度，学习功能互补向量来刻画云API和Mashup之间的潜在功能互补关系。在此基础上，将功能互补得分和功能互补向量嵌入云API推荐模型中，使功能互补关系在推荐云API的过程中起到关键性的作用。在真实世界云API数据集上进行实验，所提方法在稀疏场景下的 AUC、F1、HR@5 指标上平均提升了 2.32%、1.86%、9.15%，最终验证了所提方法可以在提高云API推荐结果准确性的同时，提升对长尾云API的推荐性能。

关键词: 云API推荐, 功能互补, 标签共现, 长尾云API

Abstract:

Current cloud application program interface (API) recommendation methods mainly use similarity calculation or historical calls of Mashup to generate recommendation results, while ignoring the beneficial functional complementarity (FC) between Mashup and cloud API.To address the above issue, a FC relationship enhanced cloud API recommendation approach was proposed.Firstly, label co-occurrence was applied to describe the FC relationship.Then, the FC score was calculated to describe the degree of FC between the cloud API and the Mashup, and the FC vector was learned to describe the potential FC relationship.Based on this, FC scores and FC vectors were embedded into the cloud API recommendation model, so that FC relationship played a key role in the cloud API recommendation process.Experiments were conducted on real-world cloud API datasets, and the AUC, F1 and HR@5 of the proposed approach improved by an average of 2.32%, 1.86% and 9.15%, respectively, in the sparse scenario.Finally, the proposed approach can improve the accuracy of cloud API recommendation results, while improving the recommendation performance of long-tail cloud API.

Key words: cloud API recommendation, functional complementarity, label co-occurrence, long tail cloud API

中图分类号:

TP393

陈真, 陈文辉, 刘啸威, 尤殿龙, 刘林林, 申利民. 功能互补关系增强的云API推荐方法[J]. 通信学报, 2023, 44(6): 125-137.

Zhen CHEN, Wenhui CHEN, Xiaowei LIU, Dianlong YOU, Linlin LIU, Limin SHEN. Functional complementarity relationship enhanced cloud API recommendation method[J]. Journal on Communications, 2023, 44(6): 125-137.

图/表 11

表1

图1

表2

图2

表3

图3

图4

图5

图6

图7

图8

参考文献 30

[1]	PAPAZOGLOU M P , HEUVEL W J V D . Service oriented architectures:approaches,technologies and research issues[J]. The VLDB Journal, 2007,16(3): 389-415.
[2]	YU J , BENATALLAH B , CASATI F ,et al. Understanding mashup development[J]. IEEE Internet Computing, 2008,12(5): 44-52.
[3]	陈真, 乞文超, 贺鹏飞 ,等. 云应用程序编程接口安全研究综述:威胁与防护[J]. 电子与信息学报, 2023,45(1): 371-382.
	CHEN Z , QI W C , HE P F ,et al. A survey for cloud application programming interface security:threats and protection[J. Journal of Electronics ＆ Information Technology, 2023,45(1): 371-382.
[4]	WU H , DUAN Y H , YUE K ,et al. Mashup-oriented Web API recommendation via multi-model fusion and multi-task learning[J]. IEEE Transactions on Services Computing, 2022,15(6): 3330-3343.
[5]	CAO B , PENG M , QING Y ,et al. Web API recommendation via combining graph attention representation and deep factorization machines quality prediction[J]. Concurrency and Computation:Practice and Experience, 2022,34(21): E7069.
[6]	ZHANG M Y , BOCKSTEDT J . Complements and substitutes in online product recommendations:the differential effects on consumers’ willingness to pay[J]. Information ＆ Management, 2020:doi.org/10.1016/j.im.2020.103341.
[7]	WANG R , WANG J , SU Z . Learning compatibility knowledge for outfit recommendation with complementary clothing matching[J]. Computer Communications, 2022,181: 320-328.
[8]	ZHANG W , CHEN Z Y , ZHA H Y ,et al. Learning from substitutable and complementary relations for graph-based sequential product recommendation[J]. ACM Transactions on Information Systems, 2022,40(2): 1-28.
[9]	WANG Z H , JIANG Z H , REN Z C ,et al. A path-constrained framework for discriminating substitutable and complementary products in E-commerce[C]// Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining. New York:ACM Press, 2018: 619-627.
[10]	MCAULEY J , PANDEY R , LESKOVEC J . Inferring networks of substitutable and complementary products[C]// Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM Press, 2015: 785-794.
[11]	HUYNH C P , CIPTADI A , TYAGI A ,et al. CRAFT:complementary recommendation by adversarial feature transform[C]// European Conference on Computer Vision. Berlin:Springer, 2019: 54-66.
[12]	BOTANGEN K A , YU J , SHENG Q Z ,et al. Geographic-aware col-laborative filtering for Web service recommendation[J]. Expert Sys-tems With Applications, 2020:doi.org/10.1016/j.eswa.2020.113347.
[13]	XIONG R , WANG J , ZHANG N ,et al. Deep hybrid collaborative filtering for Web service recommendation[J]. Expert Systems with Applications, 2018,110: 191-205.
[14]	YAO L N , WANG X Z , SHENG Q Z ,et al. Mashup recommendation by regularizing matrix factorization with API co-invocations[J]. IEEE Transactions on Services Computing, 2021,14(2): 502-515.
[15]	TIAN G , WANG J , HE K Q ,et al. Integrating implicit feedbacks for time-aware Web service recommendations[J]. Information Systems Frontiers, 2017,19(1): 75-89.
[16]	NIU H , KEIVANLOO I , ZOU Y . API usage pattern recommendation for software development[J]. Journal of Systems and Software, 2017,129: 127-139.
[17]	ALMARIMI N , OUNI A , BOUKTIF S ,et al. Web service API recommendation for automated mashup creation using multi-objective evolutionary search[J]. Applied Soft Computing, 2019,85:105830.
[18]	NA?M H , AZNAG M , DURAND N ,et al. Semantic pattern mining based Web service recommendation[C]// Proceedings of International Conference on Service-Oriented Computing. Berlin:Springer, 2016: 417-432.
[19]	DOJCHINOVSKI M , KUCHAR J , VITVAR T ,et al. Personalised graph-based selection of Web APIs[C]// Proceedings of International Semantic Web Conference. Berlin:Springer, 2012: 34-48.
[20]	RICHARDSON M , DOMINOWSKA E , RAGNO R . Predicting clicks:estimating the click-through rate for new ads[C]// Proceedings of the 16th International Conference on World Wide Web. New York:ACM Press, 2007: 521-530.
[21]	RENDLE S . Factorization machines[C]// Proceedings of IEEE International Conference on Data Mining. Piscataway:IEEE Press, 2011: 995-1000.
[22]	YU Y T , WANG Z , YUAN B . An input-aware factorization machine for sparse prediction[C]// Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. California:International Joint Conferences on Artificial Intelligence Organization, 2019: 1466-1472.
[23]	LU W T , YU Y T , CHANG Y Z ,et al. A dual input-aware factorization machine for CTR prediction[C]// Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. California:International Joint Conferences on Artificial Intelligence Organization, 2020: 3139-3145.
[24]	HE X N , CHUA T S . Neural factorization machines for sparse predictive analytics[C]// Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York:ACM Press, 2017: 355-364.
[25]	XIAO J , YE H , HE X ,et al. Attentional factorization machines:learning the weight of feature interactions via attention networks[J]. arXiv Preprint,arXiv:1708.04617, 2017.
[26]	CHENG H T , KOC L , HARMSEN J ,et al. Wide ＆ deep learning for recommender systems[C]// Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. New York:ACM Press, 2016: 7-10.
[27]	WANG R X , FU B , FU G ,et al. Deep ＆ cross network for ad click predictions[C]// Proceedings of the ADKDD’17. New York:ACM Press, 2017: 1-7.
[28]	GUO H F , TANG R M , YE Y M ,et al. DeepFM:a factorization-machine based neural network for CTR prediction[C]// Proceedings of the 26th International Joint Conference on Artificial Intelligence. New York:ACM Press, 2017: 1725-1731.
[29]	LIAN J X , ZHOU X H , ZHANG F Z ,et al. xDeepFM:combiningexplicit and implicit feature interactions for recommender systems[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery ＆ Data Mining. New York:ACM Press, 2018: 1754-1763.
[30]	SONG W , SHI C , XIAO Z ,et al. Autoint:automatic feature interaction learning via self-attentive neural networks[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management. New York:ACM Press, 2019: 1161-1170.

云API	云API标签	Mashup标签	Mashup占比
PayPal	支付	电商	37.14%
Last.FM	播客	音乐	74.03%
Twitter	博客	社交	51.63%
YouTube	视频	媒体	71.23%

模型	AUC				F1				HR@5
模型	Base	+CS	+CV	+CSCV	Base	+CS	+CV	+CSCV	Base	+CS	+CV	+CSCV
LR	0.892	0.897	0.899	0.905	0.774	0.777	0.777	0.785	0.379	0.392	0.393	0.408
FM	0.893	0.895	0.902	0.907	0.778	0.785	0.781	0.789	0.393	0.407	0.408	0.425
IFM	0.895	0.897	0.904	0.911	0.787	0.799	0.797	0.799	0.404	0.419	0.420	0.438
DIFM	0.897	0.899	0.904	0.912	0.795	0.804	0.802	0.807	0.408	0.424	0.424	0.443
NFM	0.898	0.901	0.905	0.913	0.799	0.808	0.807	0.812	0.426	0.445	0.445	0.464
AFM	0.899	0.903	0.905	0.924	0.807	0.817	0.816	0.820	0.437	0.458	0.458	0.478
WDL	0.894	0.901	0.901	0.918	0.809	0.823	0.820	0.825	0.444	0.467	0.468	0.486
DCN	0.896	0.901	0.902	0.918	0.820	0.834	0.825	0.837	0.449	0.473	0.473	0.492
DeepFM	0.898	0.905	0.905	0.925	0.826	0.838	0.837	0.843	0.457	0.482	0.483	0.502
xDeepFM	0.899	0.906	0.906	0.928	0.830	0.844	0.843	0.852	0.472	0.500	0.501	0.520
AutoInt	0.902	0.907	0.907	0.931	0.840	0.850	0.850	0.862	0.487	0.519	0.520	0.538
平均值	0.897	0.901	0.904	0.918	0.806	0.816	0.814	0.821	0.432	0.453	0.454	0.472

模型	AUC				F1				HR@5
模型	Base	+CS	+CV	+CSCV	Base	+CS	+CV	+CSCV	Base	+CS	+CV	+CSCV
LR	0.616	0.666	0.660	0.707	0.685	0.724	0.718	0.774	0.278	0.307	0.308	0.327
FM	0.619	0.667	0.663	0.709	0.688	0.726	0.721	0.791	0.288	0.319	0.319	0.339
IFM	0.622	0.669	0.663	0.710	0.694	0.728	0.727	0.795	0.296	0.329	0.330	0.352
DIFM	0.628	0.670	0.665	0.713	0.700	0.736	0.735	0.797	0.313	0.350	0.350	0.372
NFM	0.629	0.673	0.669	0.715	0.714	0.741	0.739	0.799	0.320	0.357	0.357	0.381
AFM	0.632	0.674	0.671	0.717	0.716	0.743	0.744	0.807	0.325	0.365	0.364	0.389
WDL	0.630	0.671	0.665	0.714	0.722	0.758	0.759	0.809	0.323	0.364	0.364	0.389
DCN	0.632	0.673	0.669	0.716	0.724	0.764	0.763	0.820	0.340	0.384	0.384	0.410
DeepFM	0.635	0.674	0.672	0.719	0.726	0.769	0.778	0.825	0.353	0.398	0.399	0.427
xDeepFM	0.639	0.679	0.675	0.723	0.728	0.774	0.785	0.837	0.354	0.401	0.402	0.431
AutoInt	0.642	0.681	0.680	0.728	0.732	0.789	0.787	0.840	0.369	0.419	0.419	0.450
平均值	0.629	0.672	0.669	0.716	0.712	0.750	0.751	0.809	0.324	0.363	0.363	0.388

功能互补关系增强的云API推荐方法

Functional complementarity relationship enhanced cloud API recommendation method

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 30

相关文章 15

Metrics

推荐阅读 0

[1]	李竟博, 马礼, 李阳, 傅颖勋, 马东超. 感传算协同工业互联网优化设计[J]. 通信学报, 2023, 44(6): 12-22.
[2]	赵仕祺, 黄小红, 钟志港. 基于信誉的域间路由选择机制的研究与实现[J]. 通信学报, 2023, 44(6): 47-56.
[3]	魏德宾, 潘成胜, 杨力, 颜佐任. 基于网络流量水平等级预测的自适应随机早期检测算法[J]. 通信学报, 2023, 44(6): 154-166.
[4]	李元诚, 秦永泰. 基于深度强化学习的软件定义安全中台QoS实时优化算法[J]. 通信学报, 2023, 44(5): 181-192.
[5]	夏莹杰, 朱思雨, 刘雪娇. 区块链架构下具有条件隐私的车辆编队跨信任域高效群组认证研究[J]. 通信学报, 2023, 44(4): 111-123.
[6]	谢人超, 文雯, 唐琴琴, 刘云龙, 谢高畅, 黄韬. 轨道交通移动边缘计算网络安全综述[J]. 通信学报, 2023, 44(4): 201-215.
[7]	罗智勇, 张玉, 王青, 宋伟伟. 基于贝叶斯攻击图的SDN入侵意图识别算法的研究[J]. 通信学报, 2023, 44(4): 216-225.
[8]	王一丰, 郭渊博, 陈庆礼, 方晨, 林韧昊, 周永良, 马佳利. 基于对比增量学习的细粒度恶意流量分类方法[J]. 通信学报, 2023, 44(3): 1-11.
[9]	张进, 葛强, 徐伟海, 江逸茗, 马海龙, 于洪涛. 拟态路由器BGP代理的设计实现与形式化验证[J]. 通信学报, 2023, 44(3): 33-44.
[10]	经普杰, 王良民, 董学文, 张玉书, 王骞, Muhammad Sohail. 分层跨链结构：一种面向区块链系统监管的可行架构[J]. 通信学报, 2023, 44(3): 93-104.
[11]	舒坚, 史佳伟, 刘琳岚, Manar Al-Kali. 基于时空卷积的机会网络拓扑预测[J]. 通信学报, 2023, 44(3): 145-156.
[12]	王东滨, 吴东哲, 智慧, 郭昆, 张勖, 时金桥, 张宇, 陆月明. 软件定义网络抗拒绝服务攻击的流表溢出防护[J]. 通信学报, 2023, 44(2): 1-11.
[13]	康海燕, 龙墨澜. 基于吸收马尔可夫链攻击图的网络攻击分析方法研究[J]. 通信学报, 2023, 44(2): 122-135.
[14]	张云涛, 方滨兴, 杜春来, 王忠儒, 崔志坚, 宋首友. 基于异构观测链的容器逃逸检测方法[J]. 通信学报, 2023, 44(1): 49-63.
[15]	杨宏宇, 杨海云, 张良, 成翔. 基于特征依赖图的源代码漏洞检测方法[J]. 通信学报, 2023, 44(1): 103-117.