Meta-Learning on Graph with Curvature-Based Analysis (Student Abstract)

Authors

  • Tae Hong Moon Seoul National University
  • Sungsu Lim Chungnam National University

DOI:

https://doi.org/10.1609/aaai.v34i10.7210

Abstract

Learning latent representations in graphs is finding a mapping that embeds nodes or edges as data points in a low-dimensional vector space. This paper introduces a flexible framework to enhance existing methodologies that have difficulty capturing local proximity and global relationships at the same time. Our approach generates a virtual edge between non-adjacent nodes based on the Forman-Ricci curvature in network. By analyzing the network using topological information, global relationships structurally similar can easily be detected and successfully integrated with previous works.

Downloads

Published

2020-04-03

How to Cite

Moon, T. H., & Lim, S. (2020). Meta-Learning on Graph with Curvature-Based Analysis (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13875-13876. https://doi.org/10.1609/aaai.v34i10.7210

Issue

Section

Student Abstract Track