SGR: Self-Supervised Spectral Graph Representation Learning
Abstract
Representing a graph as a vector is a challenging task; ideally, the representation should be easily computable and conducive to efficient comparisons among graphs, tailored to the particular data and analytical task at hand. Unfortunately, a "one-size-fits-all" solution is unattainable, as different analytical tasks may require different attention to global or local graph features. We develop SGR, the first, to our knowledge, method for learning graph representations in a self-supervised manner. Grounded on spectral graph analysis, SGR seamlessly combines all aforementioned desirable properties. In extensive experiments, we show how our approach works on large graph collections, facilitates self-supervised representation learning across a variety of application domains, and performs competitively to state-of-the-art methods without re-training.
Cite
@article{arxiv.1811.06237,
title = {SGR: Self-Supervised Spectral Graph Representation Learning},
author = {Anton Tsitsulin and Davide Mottin and Panagiotis Karras and Alex Bronstein and Emmanuel Müller},
journal= {arXiv preprint arXiv:1811.06237},
year = {2018}
}
Comments
As appeared in KDD Deep Learning Day workshop