Publications (15)
Orb: A Fast, Scalable Neural Network Potential
Mark Neumann, James Gin, Benjamin Rhodes +5
We introduce Orb, a family of universal interatomic potentials for atomistic modelling of materials. Orb models are 3-6 times faster than existing universal potentials, stable unde…
Automap: Towards Ergonomic Automated Parallelism for ML Models
Michael Schaarschmidt, Dominik Grewe, Dimitrios Vytiniotis +8
The rapid rise in demand for training large neural network architectures has brought into focus the need for partitioning strategies, for example by using data, model, or pipeline…
Band-gap regression with architecture-optimized message-passing neural networks
Tim Bechtel, Daniel T. Speckhard, Jonathan Godwin +1
Graph-based neural networks and, specifically, message-passing neural networks (MPNNs) have shown great potential in predicting physical properties of solids. In this work, we trai…
Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond
Jonathan Godwin, Michael Schaarschmidt, Alexander Gaunt +5
In this paper we show that simple noise regularisation can be an effective way to address GNN oversmoothing. First we argue that regularisers addressing oversmoothing should both p…
Orb-v3: atomistic simulation at scale
Benjamin Rhodes, Sander Vandenhaute, Vaidotas Å imkus +4
We introduce Orb-v3, the next generation of the Orb family of universal interatomic potentials. Models in this family expand the performance-speed-memory Pareto frontier, offering…
Pre-training via Denoising for Molecular Property Prediction
Sheheryar Zaidi, Michael Schaarschmidt, James Martens +6
Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks. In this paper, we descr…