arrow
返回

Compact network embedding for fast node classification

delete2023-04-01
delete4
PRE
AI
沈
沈肖波 (Xiaobo Shen) *
Y
Yew-Soon Ong
Shirui Pan 封面图
Shirui Pan (Shirui Pan)
刘威威 封面图
刘威威 (Weiwei Liu)
郑钰辉 封面图
郑钰辉 (Yuhui Zheng)
DOI:10.1016/j.patcog.2022.109236delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Network embedding has shown promising performance in real-world applications. The network embed-ding typically lies in a continuous vector space, where storage and computation costs are high, especially in large-scale applications. This paper proposes more compact representation to fulfill the gap. The pro-posed discrete network embedding (DNE) leverages hash code to represent node in Hamming space. The Hamming similarity between hash codes approximates the ground-truth similarity. The embedding and classifier are jointly learned to improve compactness and discrimination. The proposed multi-class classi-fier is further constrained to be discrete to expedite classification. In addition, this paper further extends DNE and proposes deep discrete attributed network embedding (DDANE) to learn compact deep embed-ding from more informative attributed network. From the perspective of generalized signal smoothing, the proposed DDANE trains an improved graph convolutional network autoencoder to effectively lever-age node attribute and network structure. Extensive experiments on node classification demonstrate the proposed methods exhibit lower storage and computational complexity than state-of-the-art network em-bedding methods, and achieve satisfactory accuracy.(c) 2022 Elsevier Ltd. All rights reserved.
Keyword:
Network embedding
Hashing
Compact representation
Graph

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.4W
被引数:
6.1W

机构

G
griffith university - gold coast campus
学者数:
4.1K
论文数: 3.5K
被引数: 6.8K
南
南洋理工大学
学者数:
4.2K
论文数: 2.0K
被引数: 5.3W
G
Griffith University
学者数:
891
论文数: 465
被引数: 1.3W
武汉大学 封面图
武汉大学
学者数:
6.9K
论文数: 2.1K
被引数: 4.9W
学者 查看更多机构
引用论文

引用论文

The 1965 Eruption of Taal Volcano
err1966-02-25
err0
PREAI
errJames G. Moore; Kazuaki Nakamura; Arturo Alcaraz
err分享
err收藏
Semi-supervised network embedding with text information
err2020-08-01
err10
PREAI
errGong, Maoguo; Yao, Chuanyu; Xie, Yu; Xu, Mingliang
err分享
err收藏
Discrete emb e dding for attribute d graphs
err2022-03-01
err8
PREAI
errYang, Hong; Chen, Ling; Pan, Shirui; Wang, Haishuai; Zhang, Peng
err分享
err收藏
Structured graph learning for clustering and semi-supervised classification
err2021-02-01
err115
errOAAI
errKang, Zhao; Peng, Chong; Cheng, Qiang; Liu, Xinwang; Peng, Xi; Xu, Zenglin; Tian, Ling
err分享
err收藏
Supervised deep hashing with a joint deep network
err2020-09-01
err26
PREAI
errChen, Yaxiong; Lu, Xiaoqiang; Li, Xuelong
err分享
err收藏
Robust discrete code modeling for supervised hashing
err2018-03-01
err100
PREAI
errLuo, Yadan; Yang, Yang; Shen, Fumin; Huang, Zi; Zhou, Pan; Shen, Heng Tao
err分享
err收藏
学者 查看更多内容