444 citations · 1.8k across the 23 of their papers we have counts for
19 papers · 1 filter
Unifying Grokking and Double Descent
Xander Davies, Lauro Langosco, David Krueger
A principled understanding of generalization in deep learning may require unifying disparate observations under a single conceptual framework. Previous work has studied \emph{grokk…
Learning rigid dynamics with face interaction graph networks
Kelsey R. Allen, Yulia Rubanova, Tatiana Lopez-Guevara +4
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions. While graph neural network (GN…
GraphCast: Learning skillful medium-range global weather forecasting
Remi Lam, Alvaro Sanchez-Gonzalez, Matthew Willson +15
Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute reso…
TF-GNN: Graph Neural Networks in TensorFlow
Oleksandr Ferludin, Arno Eigenwillig, Martin Blais +24
TensorFlow-GNN (TF-GNN) is a scalable library for Graph Neural Networks in TensorFlow. It is designed from the bottom up to support the kinds of rich heterogeneous graph data that…
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…
Physical Design using Differentiable Learned Simulators
Kelsey R. Allen, Tatiana Lopez-Guevara, Kimberly Stachenfeld +4
Designing physical artifacts that serve a purpose - such as tools and other functional structures - is central to engineering as well as everyday human behavior. Though automating…
Constraint-based graph network simulator
Yulia Rubanova, Alvaro Sanchez-Gonzalez, Tobias Pfaff +1
In the area of physical simulations, nearly all neural-network-based methods directly predict future states from the input states. However, many traditional simulation engines inst…
ETA Prediction with Graph Neural Networks in Google Maps
Austin Derrow-Pinion, Jennifer She, David Wong +14
Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time…
Large-scale graph representation learning with very deep GNNs and self-supervision
Ravichandra Addanki, Peter W. Battaglia, David Budden +8
Effectively and efficiently deploying graph neural networks (GNNs) at scale remains one of the most challenging aspects of graph representation learning. Many powerful solutions ha…
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…
Learning Mesh-Based Simulation with Graph Networks
Tobias Pfaff, Meire Fortunato, Alvaro Sanchez-Gonzalez +1
Mesh-based simulations are central to modeling complex physical systems in many disciplines across science and engineering. Mesh representations support powerful numerical integrat…
Discovering Symbolic Models from Deep Learning with Inductive Biases
Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia +4
We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The tech…
Learning to Simulate Complex Physics with Graph Networks
Alvaro Sanchez-Gonzalez, Jonathan Godwin, Tobias Pfaff +3
Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and…
Combining Q-Learning and Search with Amortized Value Estimates
Jessica B. Hamrick, Victor Bapst, Alvaro Sanchez-Gonzalez +4
We introduce "Search with Amortized Value Estimates" (SAVE), an approach for combining model-free Q-learning with model-based Monte-Carlo Tree Search (MCTS). In SAVE, a learned pri…
Object-oriented state editing for HRL
Victor Bapst, Alvaro Sanchez-Gonzalez, Omar Shams +4
We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical c…
Hamiltonian Graph Networks with ODE Integrators
Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer +1
We introduce an approach for imposing physically informed inductive biases in learned simulation models. We combine graph networks with a differentiable ordinary differential equat…
Structured agents for physical construction
Victor Bapst, Alvaro Sanchez-Gonzalez, Carl Doersch +4
Physical construction---the ability to compose objects, subject to physical dynamics, to serve some function---is fundamental to human intelligence. We introduce a suite of challen…
Graph networks as learnable physics engines for inference and control
Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg +4
Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, o…
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, i…