Trace Norm Regularised Deep Multi-Task Learning

Yongxin Yang, Timothy Hospedales

Research output: Contribution to conferencePaperpeer-review

Abstract

We propose a framework for training multiple neural networks simultaneously. The parameters from all models are regularised by the tensor trace norm, so that each neural network is encouraged to reuse others' parameters if possible -- this is the main motivation behind multi-task learning. In contrast to many deep multi-task learning models, we do not predefine a parameter sharing strategy by specifying which layers have tied parameters. Instead, our framework considers sharing for all shareable layers, and the sharing strategy is learned in a data-driven way.
Original languageEnglish
Number of pages4
Publication statusE-pub ahead of print - 16 Apr 2017
Event5th International Conference on Learning Representations - Palais des Congrès Neptune, Toulon, France
Duration: 24 Apr 201726 Apr 2017
https://iclr.cc/archive/www/2017.html

Conference

Conference5th International Conference on Learning Representations
Abbreviated titleICLR 2017
CountryFrance
CityToulon
Period24/04/1726/04/17
Internet address

Fingerprint Dive into the research topics of 'Trace Norm Regularised Deep Multi-Task Learning'. Together they form a unique fingerprint.

Cite this