TCL: Trustworthy Contrastive Learning for Web API Recommendation via Exploring Textual and Structural Semantics

With the development of service-oriented computing, software developers increasingly rely on diverse Web application programming interfaces (APIs, also known as Web services) from unmanned Web API markets. This trend aims to expedite the development of feature-rich Mashup applications while simultan...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on computational social systems pp. 1 - 12
Main Authors: Kang, Guosheng, Ren, Hongshuai, Liu, Jianxun, Cao, Buqing, Xu, Yu, Li, Pei
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
Accuracy
Contrastive learning
Electronic mail
Graph neural networks
Mashup creation
Mashups
Representation learning
Semantics
Service computing
Software
structural semantic
textual semantic
Training
trustworthy contrastive learning (TCL)
Web application programming interface (API) recommendation
ISSN:2329-924X, 2373-7476
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the development of service-oriented computing, software developers increasingly rely on diverse Web application programming interfaces (APIs, also known as Web services) from unmanned Web API markets. This trend aims to expedite the development of feature-rich Mashup applications while simultaneously reducing time and costs. However, the growing abundance of Web APIs presents a challenge in service discovery. Consequently, Web API recommendation is proposed as a vital strategy for facilitating service discovery. Nonetheless, existing approaches to Web API recommendation suffer from limitations in effectively extracting rich semantics from description documents and service networks, leading to suboptimal recommendation performance. To address this issue, this article proposes trustworthy contrastive learning (TCL) for Web API recommendation via exploring textual and structural semantics, named TCL. TCL takes the trustworthiness of both the textual and structural representations into account to differentiate the loss of contrastive learning so that both textual and structural representation learning can be mutually improved. Empirical evaluations conducted on a real-world dataset crawled from ProgrammableWeb.com demonstrate the effectiveness of the proposed approach, showcasing its superiority over baseline methods.
ISSN:2329-924X
2373-7476
DOI:10.1109/TCSS.2025.3602629