GraphMAE: Self-Supervised Masked Graph Autoencoders

Published in International Conference on Machine Learning (ICML), 2022

GraphMAE introduces masked feature reconstruction for graph neural networks and demonstrates strong transferability across graph learning tasks.

Recommended citation: Hou, Z., Liu, X., Cen, Y., Dong, Y., Jiang, H., Yang, H., Wang, C., and Tang, J. (2022). "GraphMAE: Self-Supervised Masked Graph Autoencoders." ICML.
Download Paper

GitHub