Multitask Learning without Label Correspondences

44 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Survey on Multi-Task Learning (2017, background): “In [114], two learning tasks, which share the training data, aim to maximize the mutual information to identify the correspondence between labels in different tasks.”
Adapting Auxiliary Losses Using Gradient Similarity (2018, background): “(1)In the supervised learning case when the input features are shared, this setting resembles the multi-task learning without label correspondences setting (Quadrianto et al., 2010).”
A Literature Survey on Algorithms for Multi-label Learning (2010, background): “example borrowed from [40] (6)http://dir.”
Flexible Clustered Multi-Task Learning by Learning Representative Tasks (2016, background): “The new approach allows an arbitrary task to be described by multiple representative tasks, effectively soft-assigning a task to multiple clusters with different weights.”
Robust multi-task feature learning (2012, background): “Multi-task learning has been applied successfully in a wide range of applications including object recognition [8], speech recognition [28], handwritten digits recognition [30] and disease progression prediction [44].”