Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task augmentation, in which models are trained with multiple decoders for each task. Pseudo-tasks simulate the effect of training towards closely-related tasks drawn from the same universe. In a suite of experiments, pseudo-task augmentation is shown to improve performance on single-task learning problems. When combined with multitask learning, further improvements are achieved, including state-of-the-art performance on the CelebA dataset, showing that pseudo-task augmentation and multitask learning have complementary value. All in all, pseudo-task augmentation is a broadly applicable and efficient way to boost performance in deep learning systems.

PDF

In Proceedings of the 35th International Conference on Machine Learning, 739-748, 2018.

@inproceedings{meyerson:icml18, title={Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back}, author={Elliot Meyerson and Risto Miikkulainen}, booktitle={Proceedings of the 35th International Conference on Machine Learning}, pages={739-748}, url="http://nn.cs.utexas.edu/?meyerson:icml18", year={2018} }