Dirichlet Graph Variational Autoencoder
arXiv:2010.04408
Abstract
Graph Neural Networks (GNNs) and Variational Autoencoders (VAEs) have been widely used in modeling and generating graphs with latent factors. However, there is no clear explanation of what these latent factors are and why they perform well. In this work, we present Dirichlet Graph Variational Autoencoder (DGVAE) with graph cluster memberships as latent factors. Our study connects VAEs based graph generation and balanced graph cut, and provides a new way to understand and improve the internal mechanism of VAEs based graph generation. Specifically, we first interpret the reconstruction term of DGVAE as balanced graph cut in a principled way. Furthermore, motivated by the low pass characteristics in balanced graph cut, we propose a new variant of GNN named Heatts to encode the input graph into cluster memberships. Heatts utilizes the Taylor series for fast computation of heat kernels and has better low pass characteristics than Graph Convolutional Networks (GCN). Through experiments on graph generation and graph clustering, we demonstrate the effectiveness of our proposed framework.
Inproceedings of NeurIPS 2020
References in corpus (12)
- Auto-Encoding Variational Bayes
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Neural Message Passing for Quantum Chemistry
- Variational Graph Auto-Encoders
- Learning Structural Node Embeddings Via Diffusion Wavelets
- InfoVAE: Information Maximizing Variational Autoencoders
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
- Autoencoding Variational Inference For Topic Models
- WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
- Stick-Breaking Variational Autoencoders
- Kernel Topic Models
- Dirichlet Variational Autoencoder for Text Modeling