SimilarAPI: mining analogical APIs for library migration

Research output: Chapter in Book/Report/Conference proceedingConference PaperOther

7 Citations (Scopus)


Establishing API mappings between libraries is a prerequisite stepfor library migration tasks. Manually establishing API mappings istedious due to the large number of APIs to be examined, and existingmethods based on supervised learning requires unavailable alreadyported or functionality similar applications. Therefore, we proposean unsupervised deep learning based approach to embed both APIusage semantics and API description (name and document) semantics into vector space for inferring likely analogical API mappingsbetween libraries. We implement a proof-of-concept website SimilarAPI ( which can recommend analogical APIs for 583,501 APIs of 111 pairs of analogical Java librarieswith diverse functionalities. Video:

Original languageEnglish
Title of host publicationProceedings - 2020 ACM/IEEE 42nd International Conference on Software Engineering
Subtitle of host publicationCompanion Proceedings, ICSE-Companion 2020
EditorsHyunsook Do, Tien N. Nguyen
Place of PublicationNew York NY USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9781450371223
Publication statusPublished - 2020
EventInternational Conference on Software Engineering 2020 - Online, Seoul, Korea, South
Duration: 27 Jun 202019 Jul 2020
Conference number: 42nd (Proceedings) (Website)


ConferenceInternational Conference on Software Engineering 2020
Abbreviated titleICSE 2020
Country/TerritoryKorea, South
Internet address


  • Analogical API
  • Skip thoughts
  • Word embedding

Cite this