Frecon, Jordan; Salzo, Saverio; Pontil, Massimiliano; (2021) Unveiling Groups of Related Tasks in Multi - Task Learning. In: 2020 25th International Conference on Pattern Recognition (ICPR). (pp. pp. 7134-7141). IEEE: Milan, Italy.

Preview

PDF Frecon_preprint_Unveiling_2020.pdf - Accepted Version Download (2MB) | Preview

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.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item