arrow
返回

Sparse random feature maps for the item-multiset kernel

delete2021-11-01
delete0
delete
OA
AI
S
Satoshi Oyama
M
Masahito Kurihara
DOI:10.1016/j.neunet.2021.06.024delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Random feature maps are a promising tool for large-scale kernel methods. Since most random feature maps generate dense random features causing memory explosion, it is hard to apply them to very-large-scale sparse datasets. The factorization machines and related models, which use feature combinations efficiently, scale well for large-scale sparse datasets and have been used in many applications. However, their optimization problems are typically non-convex. Therefore, although they are optimized by using gradient-based iterative methods, such methods cannot find global optimum solutions in general and require a large number of iterations for convergence. In this paper, we define the item-multiset kernel, which is a generalization of the itemset kernel and dot product kernels. Unfortunately, random feature maps for the itemset kernel and dot product kernels cannot approximate the item-multiset kernel. We thus develop a method that converts an item-multiset kernel into an itemset kernel, enabling the item-multiset kernel to be approximated by using a random feature map for the itemset kernel. We propose two random feature maps for the itemset kernel, which run faster and are more memory efficient than the existing feature map for the itemset kernel. They also generate sparse random features when the original (input) feature vector is sparse and thus linear models using proposed methods. Experiments using real-world datasets demonstrated the effectiveness of the proposed methodology: linear models using the proposed random feature maps ran from 10 to 100 times faster than ones based on existing methods. (C) 2021 The Author(s). Published by Elsevier Ltd.
Keyword:
Kernel method
Random feature
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neural Networks 封面图
Neural Networks
IF:
6.3
论文数:
8.2K
被引数:
3.0W

机构

H
Hokkaido University
学者数:
3.6W
论文数: 2.5W
被引数: 2.6W
引用论文

引用论文

Active Stimulation Site of Nucleus Accumbens Deep Brain Stimulation in Obsessive–Compulsive Disorder Is Localized in the Ventral Internal Capsule
err2013-02-15
err0
PREAI
errPepijn Munckhof; D. Andries Bosch; Mariska H. M. Mantione; Martijn Figee; Damiaan A. J. P. Denys; P. Richard Schuurman
err分享
err收藏
A core-attachment based method to detect protein complexes in PPI networks
err2009-06-02
err0
errOAAI
errMin Wu; Xiaoli Li; Chee-Keong Kwoh; See-Kiong Ng
err分享
err收藏
Lactose in Human Breast Milk an Inducer of Innate Immunity with Implications for a Role in Intestinal Homeostasis
err2013-01-10
err0
errOAAI
errAndreas Cederlund; Ylva Kai-Larsen; Gordana Printz; Hiroyuki Yoshio; Gunvor Alvelius; Hugo Lagercrantz; Roger Strömberg; Hans Jörnvall; Gudmundur H. Gudmundsson; Birgitta Agerberth
err分享
err收藏
err分享
err收藏
没有更多内容