arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.01992cs.LGcs.AIcs.CVstat.ML
收藏

通过多任务表示学习理论改进少样本学习

Improving Few-Shot Learning through Multi-task Representation Learning Theory

Université Paris-Saclay(巴黎-萨克雷大学);CEA(法国原子能委员会);Université de Lyon(里昂大学);UJM-Saint-Etienne(圣埃蒂安大学);CNRS(法国国家科学研究中心);IOGS(法国光学研究院);Institut Universitaire de France (IUF)(法国大学研究院)

Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard

AI总结:

本文利用多任务表示学习理论分析元学习算法,揭示梯度法与度量法的根本差异,并提出基于谱的正则化项改进少样本分类性能。

摘要:

在本文中,我们考虑多任务表示(MTR)学习框架,其目标是利用源任务学习一种表示,以降低解决目标任务时的样本复杂度。我们首先回顾了MTR理论的最新进展,并表明当在该框架内分析时,它们可以为流行的元学习算法提供新颖的见解。特别是,我们强调了实践中基于梯度的算法与基于度量的算法之间的一个根本差异,并提出理论分析来解释这一差异。最后,我们利用所得见解,通过一种新的基于谱的正则化项来改进元学习方法的性能,并在少样本分类基准上的实验研究中证实了其有效性。据我们所知,这是首个将MTR理论最新的学习界付诸于少样本分类任务实践的贡献。

英文摘要:

In this paper, we consider the framework of multi-task representation (MTR) learning where the goal is to use source tasks to learn a representation that reduces the sample complexity of solving a target task. We start by reviewing recent advances in MTR theory and show that they can provide novel insights for popular meta-learning algorithms when analyzed within this framework. In particular, we highlight a fundamental difference between gradient-based and metric-based algorithms in practice and put forward a theoretical analysis to explain it. Finally, we use the derived insights to improve the performance of meta-learning methods via a new spectral-based regularization term and confirm its efficiency through experimental studies on few-shot classification benchmarks. To the best of our knowledge, this is the first contribution that puts the most recent learning bounds of MTR theory into practice for the task of few-shot classification.

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。

↑