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

Autor:	Frigo, Oriel, Brossard, Rémy, Dehaene, David
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning 68T07
Druh dokumentu:	Working Paper
Popis:	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. Comment: 13 pages, 4 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2106.10124 Zobrazit plný text záznamu View this record from Arxiv