Deep Multi-task Representation Learning: A Tensor Factorisation Approach
Deep Multi-task Representation Learning: A Tensor Factorisation Approach
复制标题
DOI：
--
复制
发表时间：
2016-05
期刊：
影响因子：
--
通讯作者：
Yongxin Yang;Timothy M. Hospedales
中科院分区：
文献类型：
--
作者：
Yongxin Yang;Timothy M. Hospedales
大多数现代多任务学习方法都采用线性模型。在深度学习的时代，这种设置被认为是肤浅的。本文提出了一种新的深层多任务表征学习框架，该框架在深层网络的每一层学习跨任务共享结构。该方法将传统MTL算法显式或隐式使用的矩阵分解技术推广到张量分解，以实现深度网络中端到端知识共享的自动学习。这与需要用户定义的多任务共享策略的现有深度学习方法形成了鲜明对比。我们的方法既适用于同构MTL，也适用于异质MTL。实验证明，我们的深度多任务表征学习在更高的准确率和更少的设计选择方面都是有效的。
Most contemporary multi-task learning methods assume linear models. This setting is considered shallow in the era of deep learning. In this paper, we present a new deep multi-task representation learning framework that learns cross-task sharing structure at every layer in a deep network. Our approach is based on generalising the matrix factorisation techniques explicitly or implicitly used by many conventional MTL algorithms to tensor factorisation, to realise automatic learning of end-to-end knowledge sharing in deep networks. This is in contrast to existing deep learning approaches that need a user-defined multi-task sharing strategy. Our approach applies to both homogeneous and heterogeneous MTL. Experiments demonstrate the efficacy of our deep multi-task representation learning in terms of both higher accuracy and fewer design choices.