Detailed Information

Cited 0 time in webofscience Cited 1 time in scopus
Metadata Downloads

A Graph Embedding Technique for Weighted Graphs Based on LSTM Autoencoders

Authors
서민지이기용
Issue Date
Dec-2020
Publisher
한국정보처리학회
Keywords
Graph Embedding; Graph Similarity; LSTM Autoencoder; Weighted Graph Embedding; Weighted Graph
Citation
JIPS(Journal of Information Processing Systems), v.16, no.6, pp.1407 - 1423
Journal Title
JIPS(Journal of Information Processing Systems)
Volume
16
Number
6
Start Page
1407
End Page
1423
URI
https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/984
DOI
10.3745/JIPS.04.0197
ISSN
1976-913X
Abstract
A graph is a data structure consisting of nodes and edges between these nodes. Graph embedding is to generatea low dimensional vector for a given graph that best represents the characteristics of the graph. Recently, therehave been studies on graph embedding, especially using deep learning techniques. However, until now, mostdeep learning-based graph embedding techniques have focused on unweighted graphs. Therefore, in this paper,we propose a graph embedding technique for weighted graphs based on long short-term memory (LSTM)autoencoders. Given weighted graphs, we traverse each graph to extract node-weight sequences from the graph. Each node-weight sequence represents a path in the graph consisting of nodes and the weights between thesenodes. We then train an LSTM autoencoder on the extracted node-weight sequences and encode each nodeweightsequence into a fixed-length vector using the trained LSTM autoencoder. Finally, for each graph, wecollect the encoding vectors obtained from the graph and combine them to generate the final embedding vectorfor the graph. These embedding vectors can be used to classify weighted graphs or to search for similarweighted graphs. The experiments on synthetic and real datasets show that the proposed method is effective inmeasuring the similarity between weighted graphs.
Files in This Item
Go to Link
Appears in
Collections
공과대학 > 소프트웨어학부 > 1. Journal Articles

qrcode

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

Related Researcher

Researcher Lee, Ki Yong photo

Lee, Ki Yong
공과대학 (소프트웨어학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE