Persona2vec: a flexible multi-role representations learning framework for graphs

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.

Document Details

Document Type
Pub Defense Publication
Publication Date
Mar 30, 2021
Source ID
10.7717/peerj-cs.439

Entities

People

  • Jisung Yoon
  • Kai-Cheng Yang
  • Woo-Sung Jung
  • Yong-Yeol Ahn

Organizations

  • Air Force Office of Scientific Research
  • Asia Pacific Center for Theoretical Physics
  • Indiana University
  • Massachusetts Institute of Technology
  • Pohang University of Science and Technology

Tags

Fields of Study

  • Computer science

Readers

  • Computer Networking
  • Neural Network Machine Learning.