Can I read Dual-Primal Graph Convolutional Networks on EtoBox?

Dual-Primal Graph Convolutional Networks by Monti, Federico; Shchur, Oleksandr; Bojchevski, Aleksandar; Litany, Or; Günnemann, Stephan; Bronstein, Michael M. is a scholarly article available to read on EtoBox.

What is Dual-Primal Graph Convolutional Networks about?

In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architecture that alternates convolution-like operations on the graph and its dual. Our approach allows to learn both vertex- and edge features and generalizes the previous graph attention (GAT) model. We provide extensive experimental validation showing state-of-the-art results on a variety of tasks tested on established graph benchmarks, including CORA and Citeseer citation networks as well as MovieLens, Flixter, Douban and Yahoo Music graph-guided recommender systems.

Author

Monti, Federico; Shchur, Oleksandr; Bojchevski, Aleksandar; Litany, Or; Günnemann, Stephan; Bronstein, Michael M.

Published

2018

Language

EN