Graph Convolutional Normalizing Flows for Semi-Supervised Classification and ClusteringDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: graph convolutional network, normalizing flow, generative model
TL;DR: A normalizing flow architecture based on graphs is developed for semi-supervised learning, producing high-quality classification and clustering.
Abstract: Graph neural networks (GNNs) are \emph{discriminative models} that directly model the class posterior $p(y|\mathbf{x})$ for semi-supervised classification of graph data. While being effective for prediction, as a representation learning approach, the node representations extracted from a GNN often miss useful information for effective clustering, because that is not necessary for a good classification. In this work, we replace a GNN layer by a combination of graph convolutions and normalizing flows under a Gaussian mixture representation space, which allows us to build a \emph{generative model} that models both the class conditional likelihood $p(\mathbf{x}|y)$ and the class prior $p(y)$. The resulting neural network, GC-Flow, enjoys two benefits: it not only maintains the predictive power because of the retention of graph convolutions, but also produces high-quality clusters in the representation space, due to the structuring of the representation as a mixture of Gaussians. We demonstrate these benefits on a variety of benchmark data sets. Moreover, we show that additional parameterization, such as that on the adjacency matrix used for graph convolutions, yields additional improvement in classification and clustering.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning
13 Replies