Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning
arXiv:2104.09856
Abstract
Recently, there has been great success in applying deep neural networks on graph structured data. Most work, however, focuses on either node- or graph-level supervised learning, such as node, link or graph classification or node-level unsupervised learning (e.g. node clustering). Despite its wide range of possible applications, graph-level unsupervised learning has not received much attention yet. This might be mainly attributed to the high representation complexity of graphs, which can be represented by n! equivalent adjacency matrices, where n is the number of nodes. In this work we address this issue by proposing a permutation-invariant variational autoencoder for graph structured data. Our proposed model indirectly learns to match the node ordering of input and output graph, without imposing a particular node ordering or performing expensive graph matching. We demonstrate the effectiveness of our proposed model on various graph reconstruction and generation tasks and evaluate the expressive power of extracted representations for downstream graph-level classification and regression.
References in corpus (13)
- Learning deep representations by mutual information estimation and maximization
- Variational Graph Auto-Encoders
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- graph2vec: Learning Distributed Representations of Graphs
- Generating Long Sequences with Sparse Transformers
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- MolGAN: An implicit generative model for small molecular graphs
- Learning Deep Generative Models of Graphs
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
- InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
- Adversarially Regularized Graph Autoencoder for Graph Embedding
- Stochastic Optimization of Sorting Networks via Continuous Relaxations
- Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity