Unveiling Groups of Related Tasks in Multi-Task Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Unveiling Groups of Related Tasks in Multi-Task Learning

Abstract

A common approach in multi-task learning is to encourage the tasks to share a low dimensional representation. This has led to the popular method of trace norm regularization, which has proved effective in many applications. In this paper, we extend this approach by allowing the tasks to partition into different groups, within which trace norm regularization is separately applied. We propose a continuous bilevel optimization framework to simultaneously identify groups of related tasks and learn a low dimensional representation within each group. Hinging on recent results on the derivative of generalized matrix functions, we devise a smooth approximation of the upper-level objective via a dual forward-backward algorithm with Bregman distances. This allows us to solve the bilevel problem by a gradient-based scheme. Numerical experiments on synthetic and benchmark datasets support the effectiveness of the proposed method.
Fichier principal
Vignette du fichier
2020_Frecon_J_p-icpr_ugrtmtl.pdf (1.98 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03774122 , version 1 (09-09-2022)

Identifiers

  • HAL Id : hal-03774122 , version 1

Cite

Jordan Frecon, Saverio Salzo, Massimiliano Pontil. Unveiling Groups of Related Tasks in Multi-Task Learning. ICPR, Jan 2021, Milan, Italy. ⟨hal-03774122⟩
8 View
29 Download

Share

Gmail Facebook X LinkedIn More