Description
Multi-task learning (MTL) introduces an inductive bias, based on a-priori relations between tasks: the trainable model is compelled to model more general dependencies by using the abovementioned relation as an important data feature. Hierarchical MTL, in which different tasks use different levels of the deep neural network, provides more effective inductive bias compared to “flat” MTL. Also, hierarchical MTL helps to solve the vanishing gradient problem in deep learning.
Papers Using This Method
Hierarchical Multi-Task Learning Framework for Session-based Recommendations2023-09-12Provable Pathways: Learning Multiple Tasks over Multiple Paths2023-03-08More layers! End-to-end regression and uncertainty on tabular data with deep learning2021-12-07Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations2021-10-26Deep multi-task learning with low level tasks supervised at lower layers2016-08-01