DeepLib: Machine translation techniques to recommend upgrades for third-party libraries

作者：

Highlights：

• Upgrading history of libraries is populated as time series data.

• A system built on top of deep neural networks to predict library upgrades.

• The system provides recommendations for a single library and a set of libraries.

• The prediction performance is improved with deeper networks.

摘要

•Upgrading history of libraries is populated as time series data.•A system built on top of deep neural networks to predict library upgrades.•The system provides recommendations for a single library and a set of libraries.•The prediction performance is improved with deeper networks.

论文关键词：Mining software repositories,Deep learning,Encoder–decoder neural network,Third-party libraries upgrade

论文评审过程：Received 22 October 2021, Revised 15 April 2022, Accepted 15 April 2022, Available online 20 April 2022, Version of Record 30 April 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117267