Keyword-Driven Service Recommendation Via Deep Reinforced Steiner Tree Search

Chen, Hailong; Wu, Hao; Li, Jiahui; Wang, Xin; Zhang, Lei

doi:10.1109/tii.2022.3177411

Cited by 9 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [14] proposed a dynamic graph neural network-based model to tackle the evolution of service and the semantic gap between services and mashups. Besides, some works concentrate on other aspects of Web API recommendation, such as the diversity and compatibility of API candidate sets [34]- [36]. For instance, Kou et al [37] solved an automated Web API recommendation task as a nondeterministic polynomial problem.…”

Section: Related Workmentioning

confidence: 99%

“…For instance, Kou et al [37] solved an automated Web API recommendation task as a nondeterministic polynomial problem. Chen et al [36] proposed a keyword-based deep-reinforced Steiner tree search to recommend compatible services for mashup creation. Qi et al [38] described a new approach to recommending Web APIs for mashup creation, which utilizes historical mashup creations to ensure compatibility among the recommended APIs and includes a textual description mining step to precisely capture the developers' functional requirements.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation

Zhang,

Qin,

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Creating top-notch Mashup applications is becoming increasingly difficult with an overwhelming number of Web APIs. Researchers have developed various API recommendation techniques to help developers quickly locate the right API. In particular, deep learning-based solutions have attracted much attention due to their excellent representation learning capabilities. However, existing methods mainly use textual or graphical information, and do not fully consider the two, which may lead to suboptimal representation and damage recommendation performance. In this paper, we propose a Collaborative Mashup Embedding (CME) neural framework that integrates knowledge graph embedding and text encoding, using Node2Vec to convert entities into numerical vectors and BERT to encode text descriptions. A collaborative mashup embedding method was developed to optimize the entire model while capturing graph and text data knowledge. In addition, the representations obtained by the framework of the three recommendation models are derived. Experimental results on the ProgrammableWeb dataset indicate that our proposed method outperforms the SOTA methods in recommendation performance metrics Top@{1,5,10}. Precision and Recall have increased from 3% to 11%, while NDCG and MAP have improved from 3% to 6%.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation

Zhang,

Qin,

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…SmartCLIDE also aims to support service composition, however, it does not focus on the runtime, but rather on the design time, i.e., it supports the composition of services during the design of a business process. Chen et al (2023) proposed a keyword-driven service recommendation approach, which employs a deep reinforced Steiner tree search (K-DRSTS) on a service-keyword correlation graph (SKCG). Similarly, Bianchini et al (2018) developed a discovery and recommendation technique, considering factors such as developers' social networks and experience in web application development.…”

Section: Software Reuse In Soamentioning

confidence: 99%