English

Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining

Machine Learning 2021-06-21 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2106.10124,
  title  = {Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining},
  author = {Oriel Frigo and Rémy Brossard and David Dehaene},
  journal= {arXiv preprint arXiv:2106.10124},
  year   = {2021}
}

Comments

13 pages, 4 figures

R2 v1 2026-06-24T03:21:42.168Z