Skip to yearly menu bar Skip to main content

Poster Teaser
Workshop: Graph Representation Learning and Beyond (GRL+)

(#82 / Sess. 2) Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

Frederik Wenkel


Graph convolutional networks (GCNs) are widely used for semi-supervised node classification on graphs today. The graph structure is however only accounted for by considering the similarity of activations between adjacent nodes, in turn degrading the results. In this work, we augment GCN models by incorporating richer notions of regularity by leveraging cascades of band-pass filters, known as geometric scatterings. We introduce a new hybrid architecture for the task and demonstrate its potential on multiple graph datasets, where it outperforms leading GCN models.

Teaser video |

Chat is not available.