Transfer learning, which leverages knowledge from source domains to improve model performance in a target domain, has witnessed significant growth. Commonly, transfer learning methods assume identical feature and label spaces in both source and target domains—an approach known as homogeneous transfer learning. However, this assumption is often impractical, as domains frequently differ in their feature or label spaces, making precise data alignment both challenging and resource-intensive. Consequently, heterogeneous transfer learning (HTL), which addresses these disparities, has become an essential strategy in various tasks. In this paper, we provide an extensive review of over 60 HTL methods, covering both data-based and model-based approaches. We detail their key assumptions and algorithms, systematically categorizing them into instance-based, feature representation-based, parameter regularization, and parameter tuning techniques. We also conduct experiments to compare a few open-source HTL methods on four benchmarks and release the corresponding experimental scripts through GitHub. Furthermore, we examine applications in natural language processing, computer vision, multimodal learning, and biomedicine, with the aim of enhancing understanding and fostering further research in these areas. Our review incorporates recent advancements in HTL, including the adoption of transformer-based models and multimodal learning techniques, ensuring the discussion reflects the latest developments in the field. Additionally, we identify key limitations in current HTL research and provide systematic guidance for future investigations, highlighting areas that require further exploration and suggesting potential directions to advance the field.
更多
原文链接
分享
引用
