Related papers: Task Uncertainty Loss Reduce Negative Transfer in Asymmetric Multi-task Feature Learning

Task Uncertainty Loss Reduce Negative Transfer in Asymmetric Multi-task Feature Learning

URL: http://arxiv.org/abs/2012.09575v1
Date: Thu, 17 Dec 2020 13:30:45 GMT
Title: Task Uncertainty Loss Reduce Negative Transfer in Asymmetric Multi-task Feature Learning
Authors: Rafael Peres da Silva, Chayaporn Suphavilai, Niranjan Nagarajan
Abstract summary: Multi-task learning (MTL) can improve task performance overall relative to single-task learning (STL), but can hide negative transfer (NT) Asymmetric multitask feature learning (AMTFL) is an approach that tries to address this by allowing tasks with higher loss values to have smaller influence on feature representations for learning other tasks. We present examples of NT in two datasets (image recognition and pharmacogenomics) and tackle this challenge by using aleatoric homoscedastic uncertainty to capture the relative confidence between tasks, and set weights for task loss.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Multi-task learning (MTL) is frequently used in settings where a target task has to be learnt based on limited training data, but knowledge can be leveraged from related auxiliary tasks. While MTL can improve task performance overall relative to single-task learning (STL), these improvements can hide negative transfer (NT), where STL may deliver better performance for many individual tasks. Asymmetric multitask feature learning (AMTFL) is an approach that tries to address this by allowing tasks with higher loss values to have smaller influence on feature representations for learning other tasks. Task loss values do not necessarily indicate reliability of models for a specific task. We present examples of NT in two orthogonal datasets (image recognition and pharmacogenomics) and tackle this challenge by using aleatoric homoscedastic uncertainty to capture the relative confidence between tasks, and set weights for task loss. Our results show that this approach reduces NT providing a new approach to enable robust MTL.