ReGAE: Graph autoencoder based on recursive neural networks
This addresses a problem in graph representation learning for applications requiring scalable graph embeddings, though it appears incremental as it builds on existing recursive neural network methods.
The paper tackles the challenge of invertibly transforming large graphs into fixed-dimensional embeddings, proposing ReGAE, a graph autoencoder based on recursive neural networks, which can handle graphs with thousands of vertices as confirmed by simulation experiments.
Invertible transformation of large graphs into fixed dimensional vectors (embeddings) remains a challenge. Its overcoming would reduce any operation on graphs to an operation in a vector space. However, most existing methods are limited to graphs with tens of vertices. In this paper we address the above challenge with recursive neural networks - the encoder and the decoder. The encoder network transforms embeddings of subgraphs into embeddings of larger subgraphs, and eventually into the embedding of the input graph. The decoder does the opposite. The dimension of the embeddings is constant regardless of the size of the (sub)graphs. Simulation experiments presented in this paper confirm that our proposed graph autoencoder, ReGAE, can handle graphs with even thousands of vertices.