Meta-learning is a popular framework for learning with limited data in which an algorithm is produced by training over multiple few-shot learning tasks. For classification problems, these tasks are typically constructed by sampling a small number of support and query examples from a subset of the classes. While conventional wisdom is that task diversity should improve the performance of meta-learning, in this work we find evidence to the contrary: we propose a modification to traditional meta-learning approaches in which we keep the support sets fixed across tasks, thus reducing task diversity. Surprisingly, we find that not only does this modification not result in adverse effects, it almost always improves the performance for a variety of datasets and meta-learning methods. We also provide several initial analyses to understand this phenomenon. Our work serves to: (i) more closely investigate the effect of support set construction for the problem of meta-learning, and (ii) suggest a simple, general, and competitive baseline for few-shot learning.
Google Research（谷歌研究院）；Mila, Québec Artificial Intelligence Institute（Mila——魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；CIFAR（加拿大高等研究院）；IVADO（IVADO数据价值研究所）
Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；Tsinghua University（清华大学）；the Hong Kong University of Science and Technology（香港科技大学）；University of Chinese Academy of Sciences（中国科学院大学）
MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs
National University of Singapore（新加坡国立大学）；HeartVoice Medical Technology（心声医疗科技）；University of Science and Technology of China（中国科学技术大学）；Sir Run Run Shaw Hospital, Zhejiang University School of Medicine（浙江大学医学院附属邵逸夫医院）；Peking University（北京大学）；Institute of Medical Technology, Health Science Center of Peking University（北京大学医学部医学技术研究院）
Department of Computer Science, Stanford University（斯坦福大学计算机科学系）；Machine Learning Department, Carnegie Mellon University（卡内基梅隆大学机器学习系）；Department of Computer Science, University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校计算机科学系）
Submodular function maximization has found a wealth of new applications in machine learning models during the past years. The related supermodular maximization models (submodular minimization) also offer an abundance of applications, but they appeared to be highly intractable even under simple cardinality constraints. Hence, while there are well-developed tools for maximizing a submodular function subject to a matroid constraint, there is much less work on the corresponding supermodular maximization problems. We give a broad parameterized family of monotone functions which includes submodular …
Meta-Ensemble Learning with Diverse Data Splits for Improved Respiratory Sound Classification
Department of Electronic Engineering, Wonkwang University（Wonkwang大学电子工程系）；RSC LAB, MODULABS（MODULABS的RSC实验室）；AICU Global Inc.（AICU Global公司）；Seoul National University Bundang Hospital（首尔国立大学柏阳医院）
Neuronal diversity can improve machine learning for physics and beyond
North Carolina State University（北卡罗来纳州立大学）；The Jackson Laboratory for Genomic Medicine（杰克逊基因组医学实验室）；The College of Wooster（伍斯特学院）；Indian Institute of Science Education and Research Mohali（印度科学教育与研究学院莫哈利分校）
