Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation
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 attent...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10489941/ |
| _version_ | 1797213568987299840 |
|---|---|
| author | Chunxiang Zhang Shaowei Qin Hao Wu Lei Zhang |
| author_facet | Chunxiang Zhang Shaowei Qin Hao Wu Lei Zhang |
| author_sort | Chunxiang Zhang |
| collection | DOAJ |
| description | 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 Cooperative 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 cooperative 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%. |
| first_indexed | 2024-04-24T11:00:21Z |
| format | Article |
| id | doaj.art-0e7378e06bfb4f1c8c6b77cb617f1767 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T11:00:21Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0e7378e06bfb4f1c8c6b77cb617f17672024-04-11T23:00:48ZengIEEEIEEE Access2169-35362024-01-0112497084971910.1109/ACCESS.2024.338448710489941Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API RecommendationChunxiang Zhang0https://orcid.org/0009-0006-9287-5665Shaowei Qin1https://orcid.org/0000-0002-9774-0851Hao Wu2https://orcid.org/0000-0002-9774-0851Lei Zhang3https://orcid.org/0000-0001-8749-7459School of Information Science and Engineering, Yunnan University, Kunming, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming, ChinaSchool of Information Science and Engineering, Yunnan University, Kunming, ChinaSchool of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, ChinaCreating 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 Cooperative 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 cooperative 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%.https://ieeexplore.ieee.org/document/10489941/Mashup applicationsAPI recommendationknowledge graphcooperative embedding |
| spellingShingle | Chunxiang Zhang Shaowei Qin Hao Wu Lei Zhang Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation IEEE Access Mashup applications API recommendation knowledge graph cooperative embedding |
| title | Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation |
| title_full | Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation |
| title_fullStr | Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation |
| title_full_unstemmed | Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation |
| title_short | Cooperative Mashup Embedding Leveraging Knowledge Graph for Web API Recommendation |
| title_sort | cooperative mashup embedding leveraging knowledge graph for web api recommendation |
| topic | Mashup applications API recommendation knowledge graph cooperative embedding |
| url | https://ieeexplore.ieee.org/document/10489941/ |
| work_keys_str_mv | AT chunxiangzhang cooperativemashupembeddingleveragingknowledgegraphforwebapirecommendation AT shaoweiqin cooperativemashupembeddingleveragingknowledgegraphforwebapirecommendation AT haowu cooperativemashupembeddingleveragingknowledgegraphforwebapirecommendation AT leizhang cooperativemashupembeddingleveragingknowledgegraphforwebapirecommendation |