Mashup-Oriented Web API Recommendation via Multi-Model Fusion and Multi-Task Learning

Mashup-Oriented Web API Recommendation via Multi-Model Fusion and Multi-Task Learning
复制标题

通过多模型融合和多任务学习实现面向 Mashup 的 Web API 推荐

DOI:
10.1109/tsc.2021.3098756
复制
发表时间:
2021-07
影响因子:
8.1
通讯作者:
Zhang Lei
Zhang Lei
中科院分区:
计算机科学2区
文献类型:
--
作者:
Wu Hao;Duan Yunhao;Yue Kun;Zhang Lei

文献摘要

参考文献

被引文献

相似文献

随着Web API数量的不断增加,为mashup创建选择合适的API变得更加困难。为了解决这个问题,已经提出了各种方法来推荐API以匹配mashup的需求,并取得了很大的成功。然而,在特征融合和利用、文本需求理解、Mashup类别的利用以及兼容性评估方面存在一些挑战。因此,我们提出了一个神经框架(MTFM)的多模型融合和多任务学习的Mashup为导向的Web API推荐。MTFM利用一个语义组件来生成需求的表示,并引入一个功能交互组件来对mashup和WebAPI之间的功能交互进行建模。两个组件的输出特征进一步融合预测候选API,这使我们能够同时具有基于内容和协同过滤方法的优点。我们进一步引入mashup类别判断作为辅助任务,其中这两个任务都被视为多标签学习问题,并与多任务学习联合优化。此外,我们还将MTFM扩展到MTFM++,以利用API的元数据和质量特性,并提出了一个兼容性评估指标。ProgrammableWeb数据集上的实验结果表明,我们的方法优于最流行的国家的最先进的方法。
As the number of Web APIs ever increases, choosing the appropriate APIs for mashup creations becomes more difficult. To tackle this problem, various methods have been proposed to recommend APIs to match requirements of mashups and achieved much success. However, there existed some challenges with feature fusion and utilization, textual requirement understanding, utilization of Mashup categories and compatibility evaluation. Therefore, we propose a neural framework (MTFM) based on multi-model fusion and multi-task learning for Mashup-oriented Web API recommendation. MTFM exploits a semantic component to generate representations of requirements and introduces a feature interaction component to model the feature interaction between mashups and Web APIs. Output features of both components are further fused to predict the candidate APIs, and this enables us to have both the advantages of content-based and collaborative filtering methods. We further introduce mashup category judgment as an auxiliary task, where both tasks are viewed as a multi-label learning problem and jointly optimized with multi-task learning. Also, we have extended MTFM to MTFM++ to take advantage of the metadata and quality features of APIs, and proposed a metric for compatibility evaluation. Experimental results on the ProgrammableWeb dataset show that our methods outperform most popular state-of-the-art methods.
CSCF:一种基于内容相似度和协同过滤的混搭服务推荐方法
DOI: 10.14257/ijgdc.2014.7.2.15
发表时间: 2014-04
影响因子: --
作者:
Buqing Cao;Mingdong Tang;Xing Huang
通讯作者: Xing Huang
DOI: 10.1109/tse.2016.2624293
发表时间: 2017-07
影响因子: 7.4
作者:
Qiang He;Rui Zhou;Xuyun Zhang;Yanchun Wang;Dayong Ye;Feifei Chen;J. Grundy;Yun Yang
通讯作者: Qiang He;Rui Zhou;Xuyun Zhang;Yanchun Wang;Dayong Ye;Feifei Chen;J. Grundy;Yun Yang
DOI: 10.1109/services.2007.67
发表时间: 2007-07
期刊: 2007 IEEE Congress on Services (Services 2007)
影响因子: --
作者:
Xuanzhe Liu;Yi Hui;Wei Sun;Haiqi Liang
通讯作者: Xuanzhe Liu;Yi Hui;Wei Sun;Haiqi Liang
DOI: 10.1109/tsc.2015.2485988
发表时间: 2017-11
影响因子: 8.1
作者:
Zhiwei Yu;R. Wong;Chi-Hung Chi-Chi-Hung-Chi-36452710
通讯作者: Zhiwei Yu;R. Wong;Chi-Hung Chi-Chi-Hung-Chi-36452710
DOI: 10.1145/2950290.2950333
发表时间: 2016-11
期刊: Proceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering
影响因子: --
作者:
A. Nguyen;Michael C Hilton;Mihai Codoban;H. Nguyen;L. Mast;E. Rademacher;T. Nguyen;Danny Dig
通讯作者: A. Nguyen;Michael C Hilton;Mihai Codoban;H. Nguyen;L. Mast;E. Rademacher;T. Nguyen;Danny Dig