On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs With Missing Node Features

Emanuele Rossi, Henry Kenlay, Maria I. Gorinova 0001, Benjamin Paul Chamberlain, Xiaowen Dong 0001, Michael M. Bronstein. On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs With Missing Node Features. In Bastian Rieck, Razvan Pascanu, editors, Learning on Graphs Conference, LoG 2022, 9-12 December 2022, Virtual Event. Volume 198 of Proceedings of Machine Learning Research, pages 11, PMLR, 2022. [doi]

Abstract

Abstract is missing.