SOTAVerified

PiNet: Attention Pooling for Graph Classification

2020-08-11Code Available0· sign in to hype

Peter Meltzer, Marcelo Daniel Gutierrez Mallea, Peter J. Bentley

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We propose PiNet, a generalised differentiable attention-based pooling mechanism for utilising graph convolution operations for graph level classification. We demonstrate high sample efficiency and superior performance over other graph neural networks in distinguishing isomorphic graph classes, as well as competitive results with state of the art methods on standard chemo-informatics datasets.

Tasks

Reproductions