Variational Recurrent Neural Networks for Graph Classification
Machine Learning
2019-05-14 v4 Machine Learning
Abstract
We address the problem of graph classification based only on structural information. Inspired by natural language processing techniques (NLP), our model sequentially embeds information to estimate class membership probabilities. Besides, we experiment with NLP-like variational regularization techniques, making the model predict the next node in the sequence as it reads it. We experimentally show that our model achieves state-of-the-art classification results on several standard molecular datasets. Finally, we perform a qualitative analysis and give some insights on whether the node prediction helps the model better classify graphs.
Cite
@article{arxiv.1902.02721,
title = {Variational Recurrent Neural Networks for Graph Classification},
author = {Edouard Pineau and Nathan de Lara},
journal= {arXiv preprint arXiv:1902.02721},
year = {2019}
}
Comments
Representation Learning on Graphs and Manifolds workshop, ICLR 2019