Persona2vec: a flexible multi-role representations learning framework for graphs
Yoon, Jisung / Yang, Kai-Cheng / Jung, Woo-Sung / Ahn, Yong-Yeol
-
0
WEB OF SCIENCE
-
0
SCOPUS
-
6106
ITEM VIEW
-
170
DOWNLOAD
- Abstract
Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all characteristics of the node. However, across many domains, it is common to observe pervasively overlapping community structure, where most nodes belong to multiple communities, playing different roles depending on the contexts. Here, we proposepersona2vec, a graph embedding framework that efficiently learns multiple representations of nodes based on their structural contexts. Using link prediction-based evaluation, we show that our framework is significantly faster than the existing state-of-the-art model while achieving better performance.
- Issue Date
- 2021-03
- Publisher
- PeerJ Inc.
- Keywords(Author)
- Graph Embedding; Overlapping Community; Social Context; Social Network Analysis; Link Prediction
- DOI
- 10.7717/peerj-cs.439
- Journal Title
- PeerJ Computer Science
- Start Page
- e439
- ISSN
- 2376-5992
- Language
- English
- Files in This Item:
Click the button and follow the links to connect to the full text. (KDI CL members only)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.