Graph Neural Networks Exponentially Lose Expressive Power for Node Classification

Kenta Oono, Taiji Suzuki. Graph Neural Networks Exponentially Lose Expressive Power for Node Classification. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. [doi]

Authors

Kenta Oono

This author has not been identified. Look up 'Kenta Oono' in Google

Taiji Suzuki

This author has not been identified. Look up 'Taiji Suzuki' in Google