Transfer learning on stratified data: joint estimation transferred from strata. (August 2023)

• Record Type: Journal Article
• Authors: Gao, Yimiao; Yang, Yuehan
• Is Part Of: Pattern recognition. Volume 140(2023)
• Publication Date: 2023-08
• Subjects: Transfer learning -- Stratified data -- Penalized regression -- Semiparametric regression; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2023.109535
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Proposing an efficient method for transfer learning, called joint estimation transferred from strata (JETS). JETS overcomes the challenges of limited sample by making full use of all available information. JETS enjoys the computational advantages of many methods such as Lasso, MCP, etc. Providing theoretical guarantees for transfer learning technique. Abstract: This paper studies the target model with the help of auxiliary models from different but possibly related groups. Inspired by transfer learning, we propose a method called joint estimation transferred from strata (JETS). To obtain a sparse solution, JETS constructs a penalized framework combining a term that penalizes the target model and an additional term that penalizes the differences between auxiliary models and the target model. In this way, JETS overcomes the challenge caused by the limited samples in high-dimensional study, and obtains stable and accurate estimates regardless of whether auxiliary samples contain noisy information. We demonstrate that this method enjoys the computational advantage of the traditional methods such as the lasso. During simulations and applications, the proposed method is compared with several existing methods and JETS outperforms others.