Skip to yearly menu bar Skip to main content


Poster

MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks

Carlo Abate · Filippo Maria Bianchi

Hall 3 + Hall 2B #215
[ ] [ Project Page ]
Fri 25 Apr 7 p.m. PDT — 9:30 p.m. PDT

Abstract:

We propose a novel approach to compute the MAXCUT in attributed graphs, i.e., graphs with features associated with nodes and edges. Our approach works well on any kind of graph topology and can find solutions that jointly optimize the MAXCUT along with other objectives. Based on the obtained MAXCUT partition, we implement a hierarchical graph pooling layer for Graph Neural Networks, which is sparse, trainable end-to-end, and particularly suitable for downstream tasks on heterophilic graphs.

Live content is unavailable. Log in and register to view live content