Transfer Learning through Enhanced Sufficient Representation: Enriching Source Domain Knowledge with Target Data

TL;DR

This paper introduces TESR, a transfer learning method that enhances source domain representations with target data, allowing flexible model assumptions and improving performance in limited data scenarios.

Contribution

The paper proposes TESR, a novel transfer learning approach that estimates invariant representations and enhances them with target data, without assuming similar model structures.

Findings

TESR outperforms traditional methods in simulations.

TESR effectively adapts to different model types.

Real-world applications show improved transfer learning performance.

Abstract

Transfer learning is an important approach for addressing the challenges posed by limited data availability in various applications. It accomplishes this by transferring knowledge from well-established source domains to a less familiar target domain. However, traditional transfer learning methods often face difficulties due to rigid model assumptions and the need for a high degree of similarity between source and target domain models. In this paper, we introduce a novel method for transfer learning called Transfer learning through Enhanced Sufficient Representation (TESR). Our approach begins by estimating a sufficient and invariant representation from the source domains. This representation is then enhanced with an independent component derived from the target data, ensuring that it is sufficient for the target domain and adaptable to its specific characteristics. A notable advantage of TESR is that it does not rely on assuming similar model structures across different tasks. For example, the source domain models can be regression models, while the target domain task can be classification. This flexibility makes TESR applicable to a wide range of supervised learning problems. We explore the theoretical properties of TESR and validate its performance through simulation studies and real-world data applications, demonstrating its effectiveness in finite sample settings.