arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1605.06391cs.LG
收藏

深度多任务表示学习:张量分解方法

Deep Multi-task Representation Learning: A Tensor Factorisation Approach

Queen Mary, University of London(伦敦玛丽女王大学)

Yongxin Yang, Timothy Hospedales

摘要:

大多数当代多任务学习方法假设线性模型。这种设置在深度学习时代被认为是肤浅的。在本文中,我们提出了一个新的深度多任务表示学习框架,该框架在深度网络的每一层学习跨任务共享结构。我们的方法基于将许多传统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对比。我们的方法适用于同质和异构MTL。实验证明了我们的深度多任务表示学习在更高的准确性和更少的设计选择方面的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑