Web API recommendation via combining graph attention representation and deep factorization machines quality prediction. (10th June 2022)

• Record Type: Journal Article
• Authors: Cao, Buqing; Peng, Mi; Qing, Yueying; Liu, Jianxun; Kang, Guosheng; Li, Bing; Fletcher, Kenneth K.
• Is Part Of: Concurrency and computation. Volume 34:Number 21(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-10
• Subjects: DeepFM -- mashup application -- self‐attention mechanism -- service recommendation; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.7069
• Languages: English
• ISSNs: 1532-0626

Abstract

SUMMARY: As more and more companies and organizations encapsulate and publish their business data or resources to the Internet in the form of APIs, the number of web APIs has grown exponentially. For this reason, it has become challenging to quickly and effectively find web APIs from such a large‐scale web API collection, which meet the requirements of mashup developers. To this end, this article focuses on recommending suitable web APIs to build high‐quality mashups by classifying and integrating content‐oriented service functionality with service invocation prediction. The proposed web API recommendation method for mashup development uses graph attention representation and DeepFM quality prediction. First, it uses the web API composition and shared annotation relationships to construct a web API relationship network. Second, it applies the self‐attention mechanism to compute the attention coefficients of different neighboring nodes in the web API relationship network. So, for a specific web API node, the weighted sum of the importance of its neighboring nodes and features characterizes that web API node. Doing so ensures that the service can be divided more accurately into different functional clusters via high‐quality characterization. Third, for the web APIs in a cluster, the high‐quality representation results are combined with multidimensional quality of service attributes. It employs the DeepFM to model and mine complex interaction relationships between features and subsequently predict and rank the invocation scores of web APIs. Finally, experiments are compared and analyzed on real‐world web API datasets. It can be seen from the results of several groups of comparative experiments that the proposed method outperforms other nine baseline methods on accuracy, recall, F1, DCG, and AUC and achieved a good classification accuracy and recommendation effect.