Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
This work addresses graph generation and self-supervised pretraining for domains like molecule design, but it appears incremental as it builds on graph autoencoder concepts.
The authors tackled graph representation learning by proposing the Graph Context Encoder (GCE), which uses graph feature masking and reconstruction to generate novel graphs and improve supervised classification tasks, achieving performance gains on standard benchmarks.
We propose the Graph Context Encoder (GCE), a simple but efficient approach for graph representation learning based on graph feature masking and reconstruction. GCE models are trained to efficiently reconstruct input graphs similarly to a graph autoencoder where node and edge labels are masked. In particular, our model is also allowed to change graph structures by masking and reconstructing graphs augmented by random pseudo-edges. We show that GCE can be used for novel graph generation, with applications for molecule generation. Used as a pretraining method, we also show that GCE improves baseline performances in supervised classification tasks tested on multiple standard benchmark graph datasets.