On the unreasonable effectiveness of feature propagation in learning on graphs with missing node features

While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in...

詳細記述

書誌詳細
主要な著者: Rossi, E, Kenlay, H, Gorinova, MI, Chamberlain, BP, Dong, X, Bronstein, M
フォーマット: Conference item
言語:English
出版事項: Proceedings of Machine Learning Research 2022

類似資料