Poster

Adaptive Adversarial Multi-task Representation Learning

YUREN MAO · Weiwei Liu · Xuemin Lin

Keywords: [ Transfer and Multitask Learning ] [ Transfer, Multitask and Meta-learning ]

Abstract:

Adversarial Multi-task Representation Learning (AMTRL) methods are able to boost the performance of Multi-task Representation Learning (MTRL) models. However, the theoretical mechanism behind AMTRL is less investigated. To fill this gap, we study the generalization error bound of AMTRL through the lens of Lagrangian duality . Based on the duality, we proposed an novel adaptive AMTRL algorithm which improves the performance of original AMTRL methods. The extensive experiments back up our theoretical analysis and validate the superiority of our proposed algorithm.

Chat is not available.