# Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back

arXiv: https://arxiv.org/abs/1803.04062 · HTML: https://mlsanity.com/paper/1803.04062/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2018.

## Built on by (most cited first, 9 of 9)

- [Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning](https://mlsanity.com/paper/2106.02705/) (2021)
- [Unified Detection of Digital and Physical Face Attacks](https://mlsanity.com/paper/2104.02156/) (2021)
- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [Text Augmentation in a Multi-Task View](https://mlsanity.com/paper/2101.05469/) (2021)
- [Joint Registration and Segmentation via Multi-Task Learning for Adaptive Radiotherapy of Prostate Cancer](https://mlsanity.com/paper/2105.01844/) (2021)
- [Multi-task Learning with 3D-Aware Regularization](https://mlsanity.com/paper/2310.00986/) (2023)
- [Optimizing Airbnb Search Journey with Multi-task Learning](https://mlsanity.com/paper/2305.18431/) (2023)
- [Deep Multi-Task Learning for Malware Image Classification](https://mlsanity.com/paper/2405.05906/) (2024)
- [Learning Representation for Multitask learning through Self Supervised Auxiliary learning](https://mlsanity.com/paper/2409.16651/) (2024)

## Abstract (arXiv)

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.