1 code implementation • 11 Aug 2020 • Peter Meltzer, Marcelo Daniel Gutierrez Mallea, Peter J. Bentley
We propose PiNet, a generalised differentiable attention-based pooling mechanism for utilising graph convolution operations for graph level classification.
1 code implementation • 8 May 2019 • Peter Meltzer, Marcelo Daniel Gutierrez Mallea, Peter J. Bentley
We propose an end-to-end deep learning learning model for graph classification and representation learning that is invariant to permutation of the nodes of the input graphs.
Ranked #60 on Graph Classification on PROTEINS
no code implementations • 22 Feb 2019 • Marcelo Daniel Gutierrez Mallea, Peter Meltzer, Peter J. Bentley
Building on prior work combining explicit tensor representations with a standard image-based classifier, we propose a model to perform graph classification by extracting fixed size tensorial information from each graph in a given set, and using a Capsule Network to perform classification.
Ranked #14 on Graph Classification on PTC