Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning
This work addresses the problem of improving generalization in multi-task learning for AI practitioners, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the challenge of finding flexible and accurate shared architectures in multi-task learning by proposing a Task Adaptive Activation Network (TAAN) that learns optimal activation functions per task, with functional regularization methods to enhance performance, as shown in comprehensive experiments.
Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate architecture that can be shared among multiple tasks. In this paper, we propose a novel deep learning model called Task Adaptive Activation Network (TAAN) that can automatically learn the optimal network architecture for MTL. The main principle of TAAN is to derive flexible activation functions for different tasks from the data with other parameters of the network fully shared. We further propose two functional regularization methods that improve the MTL performance of TAAN. The improved performance of both TAAN and the regularization methods is demonstrated by comprehensive experiments.