Network Embedding Using Sparse Approximations of Random Walks
Machine Learning
2023-08-29 v1
Abstract
In this paper, we propose an efficient numerical implementation of Network Embedding based on commute times, using sparse approximation of a diffusion process on the network obtained by a modified version of the diffusion wavelet algorithm. The node embeddings are computed by optimizing the cross entropy loss via the stochastic gradient descent method with sampling of low-dimensional representations of green functions. We demonstrate the efficacy of this method for data clustering and multi-label classification through several examples, and compare its performance over existing methods in terms of efficiency and accuracy. Theoretical issues justifying the scheme are also discussed.
Cite
@article{arxiv.2308.13663,
title = {Network Embedding Using Sparse Approximations of Random Walks},
author = {Paula Mercurio and Di Liu},
journal= {arXiv preprint arXiv:2308.13663},
year = {2023}
}
Comments
20 pages, 4 figures