Automated Unsupervised Graph Representation Learning
Published in IEEE Transactions on Knowledge and Data Engineering (TKDE), 2021
AutoProNE automatically searches for a unique optimal set of graph filters for any input dataset. It consistently and significantly enhances the expressive power of graph representations from both network embedding methods and GNNs.
Recommended citation: Hou, Z., Cen, Y., Dong, Y., Zhang, J., and Tang, J. (2021). "Automated Unsupervised Graph Representation Learning." IEEE TKDE.
Download Paper