Publication

Memory-Based Graph Networks

AbstractGraph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also introduce two new networks based on this layer: memory-based GNN (MemGNN) and graph memory network (GMN) that can learn hierarchical graph representations. The experimental results shows that the proposed models achieve state-of-the-art results in eight out of nine graph classification and regression benchmarks. We also show that the learned representations could correspond to chemical features in the molecule data.

Download publication

Related Resources

See what’s new.

Publication

2009

Constant mean curvature hypersurfaces in the (n+1)-sphere by gluing spherical building blocks

The techniques developed by Butscher (Gluing constructions amongst…

Publication

2015

3D Visualization Of Cadnano And Protein Data Using A Cloud Streaming Framework For Web-Based Large Model Viewing

Available on request…

Publication

2022

It’s Over There: Designing an Intelligent Virtual Agent That Can Point Accurately into the Real World

It is challenging to design an intelligent virtual agent (IVA) that…

Project

2017

Project Dreamcatcher: Generative Design Solutions in CAD

What if a CAD system could generate thousands of design options that…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us