A paper accepted for SDM2021

Our paper proposing the use of random features to increase the representation power of GNNs and its strong theoretical guarantees was accepted for SIAM Conference on Data Mining Conference (SDM 2021).

Ryoma Sato, Makoto Yamada, Hisashi Kashima.
Random Features Strengthen Graph Neural Networks.
In Proceedings of SIAM International Conference on Data Mining (SDM), 2021.