NAFM: Neural and Attentional Factorization Machine for Web API Recommendation

With the wide adoption of SOA (Service Oriented Architecture), a massive amount of innovative applications emerge on the Internet. One of the popular representations is Mashup composed of multiple Web APIs. Recommending desirable Web APIs to develop Mashup applications has attracted much attention. A dozen of service recommendation approaches are proposed by incorporating multi-dimensional features extracted from service repository into recommendation models. Among the existing works, factorization machine based models show better performance than traditional collaborative filtering techniques in accuracy. However, they either model factorized interactions with the same weight or neglect the non-linear and complex inherent structure of real-world data. In real-world applications, different predictor variables usually have different predictive power, and not all features contain useful signal for estimating the target. Moreover, higher-order feature interactions are usually underlain in real-world data. To address these drawbacks, this paper proposes a hybrid factorization machine model with a novel neural network architecture named NAFM by integrating deep neural network to capture the non-linear feature interactions and attention mechanism to capture the different importance of feature interactions. Comprehensive experiments on a real-world dataset show that the proposed approach outperforms the other state-of-the-art models for service recommendation.

I. Introduction

Mashups are a new type of Web application that leverages contents coming from different data sources to create completely new and innovative services. Web APIs (also called services in this paper) with different functionality can be composed to generate novel and value-added services. Mashuping Web APIs makes the application creation easier to developers. And Mashup applications have well scalability due to the composition way. Inspired by the advantages of Mashup technology and the economic benefits of Mashups, some Mashup tools or platforms have emerged on the Internet, such as WireCloud¹

https://wirecloud.readthedocs.io/en/latest/

, Linked Widgets²

http://linkedwidgets.org/

, and ProgrammableWeb³

https://www.programmableweb.com/

. These tools or platforms accelerate the prevalence of Mashup applications for the low barriers to access and develop. As a result, a large number of Web APIs and Mashup applications are released on the Internet. Take ProgrammableWeb platform as an example, until 2019, there are more than 20,000 services and more than 7,900 Mashups, and the number continues to grow. In such a huge number of APIs on the Web, how to identify suitable APIs for Mashup creation becomes a hot and challenging issue.