Web API recommendation is a popular technology in service-oriented software development and application. They reduce the costs of time and space in service searching and discovery process, which greatly facilitates Web API based Mashup creation. However, the efficiency and ACC of some recent recommendation methods still need to be improved due to their limited representation in fuzing network topology and node feature of service, and the neglected higher-order feature interactions between Web APIs. The proposed Web API recommendation method that integrates AMC graph representation learning and xDeepFM quality prediction in this article overcame these limitations. A series of experiments are conducted on real datasets crawled from the ProgrammableWeb, and a significant increase in classification performance and recommendation quality is shown for the proposed method. It is of great significance for Web APIs based Mashup creation, as well as service-oriented software development and appl...

With the increasing number of Web services, how to provide developers with Web APIs that meet their Mashup requirements accurately and efficiently has become a challenge. Even though the existing methods show improvements in service recommendation, the efficiency and accuracy (ACC) of them still need to be improved due to their limited representation in fuzing network topology and node feature of Web service, and the neglected higher-order feature interactions of Web service. To address this problem, this article proposes a Web APIs recommendation method via combining adaptive multichannel (AMC) graph representation and eXtreme deep factorization machine (xDeepFM) quality prediction. In this method, firstly, specific embedding and shared embedding in Web API node isomorphic network are extracted from the nodes’ feature space, topology space, and the combination of the two spaces. Then, attention mechanism is used to adaptively learn the importance weight of each embedding. Next, these ...