36 citations · 70 across the 16 of their papers we have counts for
16 papers
GPS++: Reviving the Art of Message Passing for Molecular Property Prediction
Dominic Masters, Josef Dean, Kerstin Klaser +9
We present GPS++, a hybrid Message Passing Neural Network / Graph Transformer model for molecular property prediction. Our model integrates a well-tuned local message passing compo…
Efficient and Sound Differentiable Programming in a Functional Array-Processing Language
Amir Shaikhha, Mathieu Huot, Shabnam Ghasemirad +3
Automatic differentiation (AD) is a technique for computing the derivative of a function represented by a program. This technique is considered as the de-facto standard for computi…
BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion
Alberto Cattaneo, Daniel Justus, Harry Mellor +7
We present the award-winning submission to the WikiKG90Mv2 track of OGB-LSC@NeurIPS 2022. The task is link-prediction on the large-scale knowledge graph WikiKG90Mv2, consisting of…
Tuple Packing: Efficient Batching of Small Graphs in Graph Neural Networks
Mario Michael Krell, Manuel Lopez, Sreenidhi Anand +2
When processing a batch of graphs in machine learning models such as Graph Neural Networks (GNN), it is common to combine several small graphs into one overall graph to accelerate…
FLAG: Flow-based 3D Avatar Generation from Sparse Observations
Sadegh Aliakbarian, Pashmina Cameron, Federica Bogo +2
To represent people in mixed reality applications for collaboration and communication, we need to generate realistic and faithful avatar poses. However, the signal streams that can…
Hashing Modulo Alpha-Equivalence
Krzysztof Maziarz, Tom Ellis, Alan Lawrence +2
In many applications one wants to identify identical subtrees of a program syntax tree. This identification should ideally be robust to alpha-renaming of the program, but no existi…