ABSTRACT
With the ever-increasing popularity of microservice architecture, a considerable number of enterprises or organizations have encapsulated their complex business services into various lightweight functions as published them accessible APIs (Application Programming Interfaces). Through keyword search, a software developer could select a set of APIs from a massive number of candidates to implement the functions of a complex mashup, which reduces the development cost significantly. However, traditional keyword search methods for APIs often suffer from several critical issues such as functional compatibility and limited diversity in search results, which may lead to mashup creation failures and lower development productivity. To deal with these challenges, this paper designs DAWAR, a diversity-aware Web APIs recommendation approach that finds diversified and compatible APIs for mashup creation. Specifically, the APIs recommendation problem for mashup creating is modelled as a graph search problem that aims to find the minimal group Steiner trees in a correlation graph of APIs. DAWAR innovatively employs the determinantal point processes to diversify the recommended results. Empirical evaluation is performed on commonly-used real-world datasets, and the statistic results show that DAWAR is able to achieve significant improvements in terms of recommendation diversity, accuracy, and compatibility.
Supplemental Material
- Moayad Alshangiti, Weishi Shi, Xumin Liu, and Qi Yu. 2020. A Bayesian learning model for design-phase service mashup popularity prediction. Expert Systems with Applications 149 (2020), 113231.Google ScholarCross Ref
- M Brian Blake and Michael E Nowlan. 2010. Knowledge discovery in services (KDS): Aggregating software services to discover enterprise mashups. TKDE'10 23, 6 (2010), 889--901.Google Scholar
- Alexei Borodin. 2009. Determinantal point processes. arXiv preprint arXiv:0911.1153 (2009).Google Scholar
- Allan Borodin, Aadhar Jain, Hyun Chul Lee, and Yuli Ye. 2017. Max-sum diversi- fication, monotone submodular functions, and dynamic updates. TALG'17 13, 3 (2017), 1--25.Google Scholar
- J. Carbonell and J Goldstein. 1998. The Use of MMR, Diversity-Based Reranking for Reordering Dosuments and Producing SUmmaries. In SIGIR'98, 335--336.Google Scholar
- Laming Chen, Guoxin Zhang, and Hanning Zhou. 2017. Improving the diversity of top-N recommendation via determinantal point process. In Large Scale Recommendation Systems Workshop.Google Scholar
- Laming Chen, Guoxin Zhang, and Hanning Zhou. 2018. Fast greedy map infer- ence for determinantal point process to improve recommendation diversity. In NeurIPS'18. 5627--5638.Google Scholar
- Nanxi Chen, Nicolas Cardozo, and Siobhan Clarke. 2016. Goal-driven service composition in mobile and pervasive computing. TSC'16 11, 1 (2016), 49--62.Google Scholar
- H. Cheng, M. Zhong, and J. Wang. 2020. Diversified keyword search based web service composition. The Journal of Systems and Software 163 (2020), 110540.1--110540.14.Google ScholarCross Ref
- Lu Gan, Diana Nurbakova, Léa Laporte, and Sylvie Calabretto. 2020. Enhancing Recommendation Diversity using Determinantal Point Processes on Knowledge Graphs. In SIGIR'20. 2001--2004.Google ScholarDigital Library
- Wei Gao and Jian Wu. 2017. A novel framework for service set recommendation in mashup creation. In 2017 IEEE International Conference on Web Services (ICWS). IEEE, 65--72.Google ScholarCross Ref
- Michael R Garey and David S. Johnson. 1977. The rectilinear Steiner tree problem is NP-complete. SIAM J. Appl. Math. 32, 4 (1977), 826--834.Google ScholarDigital Library
- Mike Gartrell, Ulrich Paquet, and Noam Koenigstein. 2016. Bayesian low-rank determinantal point processes. In RecSys'16. 349--356.Google Scholar
- Wenwen Gong, Chao Lv, Yucong Duan, Zengguang Liu, Mohammad R Khosravi, Lianyong Qi, and Wanchun Dou. 2020. Keywords-driven web APIs group recommendation for automatic app service creation process. https://doi.org/10.1002/ spe.2902.Google Scholar
- Wenwen Gong, Huiping Wu, Xiaokang Wang, Xuyun Zhang, Yawei Wang, Yifei Chen, and Mohammad R. Khosravi. 2021. Diversified and Compatible Web APIs Recommendation based on Game Theory in IoT. arXiv preprint arXiv: 2107.10538 (2021).Google Scholar
- Ohad Greenshpan, Tova Milo, and Neoklis Polyzotis. 2009. Autocompletion for mashups. VLDB'09 2, 1 (2009), 538--549.Google ScholarDigital Library
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In SIGKDD'16. 855--864.Google ScholarDigital Library
- Bowen Hao, Jing Zhang, Hongzhi Yin, Cuiping Li, and Hong Chen. 2021. PreTraining Graph Neural Networks for Cold-Start Users and Items Representation. In WSDM'21. 265--273.Google Scholar
- Qiang He, Bo Li, Feifei Chen, John Grundy, Xin Xia, and Yun Yang. 2020. Di- versified third-party library prediction for mobile app development. https: //doi.org/10.1109/TSE.2020.2982154.Google ScholarDigital Library
- Qiang He, Rui Zhou, Xuyun Zhang, Yanchun Wang, Dayong Ye, Feifei Chen, Shiping Chen, John Grundy, and Yun Yang. 2017. Efficient keyword search for building service-based systems based on dynamic programming. In ICSOC'17. 462--470.Google ScholarDigital Library
- Qiang He, Rui Zhou, Xuyun Zhang, Yanchun Wang, Dayong Ye, Feifei Chen, John C Grundy, and Yun Yang. 2016. Keyword search for building service-based systems. TSE'16 43, 7 (2016), 658--674.Google Scholar
- Cheng Hsu and Cheng-Te Li. 2021. RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation. In WWW'21. 2968--2979.Google Scholar
- Gang Huang, Yun Ma, Xuanzhe Liu, Yuchong Luo, Xuan Lu, and M Brian Blake. 2014. Model-based automated navigation and composition of complex service mashups. TSC'14 8, 3 (2014), 494--506.Google Scholar
- Minhao Jiang, Ada Wai-Chee Fu, and Raymond Chi-Wing Wong. 2015. Exact top-k nearest keyword search in large networks. In SIGMOD'15. 393--404.Google ScholarDigital Library
- F. K. Hwang, Dana Richards, and Pawel. Winter. 1992. The Steiner Tree Problem. Networks 22, 1 (1992), 55--89.Google ScholarCross Ref
- Alex Kulesza and Ben Taskar. 2010. Structured determinantal point processes. Advances in neural information processing systems 23 (2010), 1171--1179.Google Scholar
- Alex Kulesza and Ben Taskar. 2011. Learning determinantal point processes. UAI'11 (2011).Google Scholar
- Alex Kulesza and Ben Taskar. 2012. Determinantal point processes for machine learning. arXiv preprint arXiv:1207.6083 (2012).Google ScholarCross Ref
- B. Li, Q He, Chen Feifei, Xia Xin, Li Li, Grundy John, and Yang Yun. 2021. Em- bedding App-Library Graph for Neural Third Party Library Recommendation. In ESEC/FSE '21, Accepted.Google ScholarDigital Library
- Yandong Li, Liqiang Wang, Tianbao Yang, and Boqing Gong. 2018. How local is the local diversity? reinforcing sequential determinantal point processes with dynamic ground sets for supervised video summarization. In ECCV'18. 151--167.Google ScholarDigital Library
- Yong Liu, Yingtai Xiao, Qiong Wu, Chunyan Miao, Juyong Zhang, Binqiang Zhao, and Haihong Tang. 2020. Diversified interactive recommendation with implicit feedback. In AAAI'20, Vol. 34. 4932--4939.Google ScholarCross Ref
- Yong Liu, Yinan Zhang, Qiong Wu, Chunyan Miao, Lizhen Cui, Binqiang Zhao, Yin Zhao, and Lu Guan. 2019. Diversity-promoting deep reinforcement learning for interactive recommendation. arXiv preprint arXiv:1903.07826 (2019).Google Scholar
- Yuanfu Lu, Chuan Shi, Linmei Hu, and Zhiyuan Liu. 2019. Relation structure- aware heterogeneous information network embedding. In AAAI'19, Vol. 33. 4456--4463.Google ScholarDigital Library
- Yutao Ma, Xiao Geng, and Jian Wang. 2020. A Deep Neural Network With Multiplex Interactions for Cold-Start Service Recommendation. TEM'20 68, 1 (2020), 105--119.Google Scholar
- Qiao Maoying, Yu Jun, Liu Tongliang, Wang Xinchao, and Tao Dacheng. 2020. Diversified Bayesian Nonnegative Matrix Factorization. In AAAI'20, Vol. 34. 5420--5427.Google Scholar
- Manuel Mazzara, Nicola Dragoni, Antonio Bucchiarone, Alberto Giaretta, Stephan T. Larsen, and Schahram Dustdar. 2018. Microservices: Migration of a Mission Critical System. https://doi.org/10.1109/TSC.2018.2889087., 1 pages.Google Scholar
- Bibek Paudel and Abraham Bernstein. 2021. Random Walks with Erasure: Diver- sifying Personalized Recommendations on Social and Information Networks. In WWW'21. 2046--2057.Google ScholarDigital Library
- Lianyong Qi, Qiang He, Feifei Chen, Wanchun Dou, and Qiang Ni. 2020. Data- Driven Web APIs Recommendation for Building Web Applications. https://doi. org/10.1109/TBDATA.2020.2975587.Google Scholar
- Lianyong Qi, Qiang He, Feifei Chen, Wanchun Dou, Shaohua Wan, Xuyun Zhang, and Xiaolong Xu. 2019. Finding All You Need: Web APIs Recommendation in Web of Things Through Keywords Search. TCSS'19 6, 5 (2019), 1063--1072.Google Scholar
- Lianyong Qi, Houbing Song, Xuyun Zhang, Gautam Srivastava, Xiaolong Xu, and Shui Yu. 2021. Compatibility-Aware Web API Recommendation for Mashup Creation via Textual Description Mining. TMCCA'21 17, 1s (2021), 1--19.Google ScholarDigital Library
- Qiaoyu Tan, Ninghao Liu, Xing Zhao, Hongxia Yang, Jingren Zhou, and Xia Hu. 2020. Learning to hash with graph neural networks for recommender systems. In WWW'20. 1988--1998.Google ScholarDigital Library
- Shulong Tan, Zhixin Zhou, Zhaozhuo Xu, and Ping Li. 2020. Fast item ranking under neural network based measures. In WSDM'20. 591--599.Google ScholarDigital Library
- Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. 2019. Neural graph collaborative filtering. In SIGIR'19. 165--174.Google ScholarDigital Library
- Mark Wilhelm, Ajith Ramanathan, Alexander Bonomo, Sagar Jain, Ed H Chi, and Jennifer Gillenwater. 2018. Practical diversified recommendations on youtube with determinantal point processes. In CIKM'18. 2165--2173.Google ScholarDigital Library
- Le Wu, Lei Chen, Pengyang Shao, Richang Hong, Xiting Wang, and Meng Wang. 2021. Learning Fair Representations for Bipartite Graph based Recommendation. (2021), arXiv--2102.Google Scholar
- Fang Xie, Jian Wang, Ruibin Xiong, Neng Zhang, Yutao Ma, and Keqing He. 2019. An integrated service recommendation approach for service-based system development. Expert Systems With Applications 123 (2019), 178--194.Google ScholarDigital Library
- Lina Yao, Xianzhi Wang, Quan Z Sheng, Boualem Benatallah, and Chaoran Huang. 2018. Mashup recommendation by regularizing matrix factorization with API co-invocations. TSC'18 14, 2 (2018), 502--515.Google Scholar
- Guangba Yu, Pengfei Chen, and Zibin Zheng. 2020. Microscaler: Cost-effective Scaling for Microservice Applications in the Cloud with an Online Learning Approach. https://doi.org/10.1109/TCC.2020.2985352., 1 pages.Google Scholar
- Jin Yu, Boualem Benatallah, Fabio Casati, and Florian Daniel. 2008. Understanding mashup development. IEEE Internet computing 12, 5 (2008), 44--52.Google ScholarDigital Library
- Hailiang Zhao, Shuiguang Deng, Zijie Liu, Jianwei Yin, and Schahram Dustdar. 2020. Distributed Redundancy Scheduling for Microservice-based Applications at the Edge. https://doi.org/10.1109/TSC.2020.3013600., 1 pages.Google Scholar
Index Terms
- DAWAR: Diversity-aware Web APIs Recommendation for Mashup Creation based on Correlation Graph
Recommendations
Compatibility-Aware Web API Recommendation for Mashup Creation via Textual Description Mining
With the ever-increasing prosperity of web Application Programming Interface (API) sharing platforms, it is becoming an economic and efficient way for software developers to design their interested mashups through web API re-use. Generally, a software ...
Collaborative APIs recommendation for Artificial Intelligence of Things with information fusion
AbstractWith the rapid development of Artificial Intelligence of Things (AIoT), many applications are developed and deployed, especially mobile applications and edge applications. Many softwares are developed to support such diverse ...
Highlights- Propose a joint MF technique for information fusion for AIoT.
- Build a ...
Open APIs recommendation with an ensemble-based multi-feature model
AbstractRecommending the appropriate APIs from a large volume of Open APIs to application developers both accurately and efficiently has become a challenging problem. Established work usually takes only one feature of Open APIs into account, ...
Highlights- We propose an ensemble-based approach to Open APIs recommendation with a multiple feature model.
Comments