CASIA OpenIR  > 模式识别国家重点实验室  > 先进时空数据分析与学习
Structure-Aware Convolutional Neural Networks
Chang, Jianlong1
2018
Conference NameAdvances in Neural Information Processing Systems 31
Conference Date2018.12
Conference Place加拿大
Abstract

Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures. It causes that CNNs are allowed to manage data with Euclidean or grid-like structures (e.g., images), not ones with non-Euclidean or graph structures (e.g., traffic networks). To broaden the reach of CNNs, we develop structure-aware convolution to eliminate the invariance, yielding a unified mechanism of dealing with both Euclidean and non-Euclidean structured data. Technically, filters in the structure-aware convolution are generalized to univariate functions, which are capable of aggregating local inputs with diverse topological structures. Since infinite parameters are required to determine a univariate function, we parameterize these filters with numbered learnable parameters in the context of the function approximation theory. By replacing the classical convolution in CNNs with the structure-aware convolution, Structure-Aware Convolutional Neural Networks (SACNNs) are readily established. Extensive experiments on eleven datasets strongly evidence that SACNNs outperform current models on various machine learning tasks, including image classification and clustering, text categorization, skeleton-based action recognition, molecular activity detection, and taxi flow prediction.

KeywordStructure-Aware Convolution
MOST Discipline Catalogue工学
Indexed ByEI
Funding ProjectBeijing Natural Science Foundation[L172053] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61773377] ; National Natural Science Foundation of China[61573352] ; National Natural Science Foundation of China[91646207] ; Beijing Natural Science Foundation[L172053]
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/39166
Collection模式识别国家重点实验室_先进时空数据分析与学习
Affiliation1.中国科学院自动化研究所
2.中国科学院大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Chang, Jianlong. Structure-Aware Convolutional Neural Networks[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
4-SACNN-NeurIPS.pdf(1401KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chang, Jianlong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chang, Jianlong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chang, Jianlong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 4-SACNN-NeurIPS.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.