Few-shot text and image classification via analogical transfer learning

Publication Type:
Journal Article
ACM Transactions on Intelligent Systems and Technology, 2018, 9 (6)
Issue Date:
Filename Description Size
a71-liu.pdfPublished Version2.27 MB
Adobe PDF
Full metadata record
© 2018 ACM. Learning from very few samples is a challenge for machine learning tasks, such as text and image classifcation. Performance of such task can be enhanced via transfer of helpful knowledge from related domains, which is referred to as transfer learning. In previous transfer learning works, instance transfer learning algorithms mostly focus on selecting the source domain instances similar to the target domain instances for transfer. However, the selected instances usually do not directly contribute to the learning performance in the target domain. Hypothesis transfer learning algorithms focus on the model/parameter level transfer. They treat the source hypotheses as well-trained and transfer their knowledge in terms of parameters to learn the target hypothesis. Such algorithms directly optimize the target hypothesis by the observable performance improvements. However, they fail to consider the problem that instances that contribute to the source hypotheses may be harmful for the target hypothesis, as instance transfer learning analyzed. To relieve the aforementioned problems, we propose a novel transfer learning algorithm, which follows an analogical strategy. Particularly, the proposed algorithm frst learns a revised source hypothesis with only instances contributing to the target hypothesis. Then, the proposed algorithm transfers both the revised source hypothesis and the target hypothesis (only trained with a few samples) to learn an analogical hypothesis. We denote our algorithm as Analogical Transfer Learning. Extensive experiments on one synthetic dataset and three real-world benchmark datasets demonstrate the superior performance of the proposed algorithm.
Please use this identifier to cite or link to this item: