Lautum Regularization for Semi-supervised Transfer Learning
This work addresses performance issues in transfer learning for deep learning applications, particularly when source and target data distributions differ, offering a novel regularization approach.
The paper tackles the problem of distribution discrepancies in semi-supervised transfer learning by proposing a Lautum information-based regularization method to improve neural network transferability, demonstrating effectiveness in various experiments.
Transfer learning is a very important tool in deep learning as it allows propagating information from one "source dataset" to another "target dataset", especially in the case of a small number of training examples in the latter. Yet, discrepancies between the underlying distributions of the source and target data are commonplace and are known to have a substantial impact on algorithm performance. In this work we suggest a novel information theoretic approach for the analysis of the performance of deep neural networks in the context of transfer learning. We focus on the task of semi-supervised transfer learning, in which unlabeled samples from the target dataset are available during the network training on the source dataset. Our theory suggests that one may improve the transferability of a deep neural network by imposing a Lautum information based regularization that relates the network weights to the target data. We demonstrate the effectiveness of the proposed approach in various transfer learning experiments.