Search Results for author:
Found 23 papers, 14 papers with code
On the Scalability of GNNs for Molecular Graphs
However, structure-based architectures such as Graph Neural Networks (GNNs) are yet to show the benefits of scale mainly due to the lower efficiency of sparse operations, large data requirements, and lack of clarity about the effectiveness of various architectures.
Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images.
Generating QM1B with PySCF$_{\text{IPU}}$
Similar benefits are yet to be unlocked for quantum chemistry, where the potential of deep learning is constrained by comparatively small datasets with 100k to 20M training examples.
Role of Structural and Conformational Diversity for Machine Learning Potentials
In the field of Machine Learning Interatomic Potentials (MLIPs), understanding the intricate relationship between data biases, specifically conformational and structural diversity, and model generalization is critical in improving the quality of Quantum Mechanics (QM) data generation efforts.
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
Recently, pre-trained foundation models have enabled significant advancements in multiple fields.
Graph Positional and Structural Encoder
Positional and structural encodings (PSE) enable better identifiability of nodes within a graph, as in general graphs lack a canonical node ordering.
GPS++: Reviving the Art of Message Passing for Molecular Property Prediction
We present GPS++, a hybrid Message Passing Neural Network / Graph Transformer model for molecular property prediction.
Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration
Existing GNN benchmarking methods for molecular representation learning focus on comparing the GNNs' performances on some node/graph classification/regression tasks on certain datasets.
GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction
This technical report presents GPS++, the first-place solution to the Open Graph Benchmark Large-Scale Challenge (OGB-LSC 2022) for the PCQM4Mv2 molecular property prediction task.
Long Range Graph Benchmark
Graph Neural Networks (GNNs) that are based on the message passing (MP) paradigm generally exchange information between 1-hop neighbors to build node representations at each layer.
Ranked #3 on
Link Prediction
on PCQM-Contact
Recipe for a General, Powerful, Scalable Graph Transformer
We propose a recipe on how to build a general, powerful, scalable (GPS) graph Transformer with linear complexity and state-of-the-art results on a diverse set of benchmarks.
Ranked #1 on
Graph Property Prediction
on ogbg-ppa
3D Infomax improves GNNs for Molecular Property Prediction
Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts.
3D Pre-training improves GNNs for Molecular Property Prediction
Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts.
Rethinking Graph Transformers with Spectral Attention
Here, we present the $\textit{Spectral Attention Network}$ (SAN), which uses a learned positional encoding (LPE) that can take advantage of the full Laplacian spectrum to learn the position of each node in a given graph.
Directional Graph Networks
Then, we propose the use of the Laplacian eigenvectors as such vector field.
Ranked #2 on
Node Classification
on PATTERN 100k
Principal Neighbourhood Aggregation for Graph Nets
Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data.
Ranked #4 on
Node Classification
on PATTERN 100k
Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration
Current research in convolutional neural networks (CNN) focuses mainly on changing the architecture of the networks, optimizing the hyper-parameters and improving the gradient descent.
Saliency Enhancement using Gradient Domain Edges Merging
In recent years, there has been a rapid progress in solving the binary problems in computer vision, such as edge detection which finds the boundaries of an image and salient object detection which finds the important object in an image.
Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks
The objective of this paper is to show that saliency convolutional neural networks (CNN) can be improved by using a Green's function convolution (GFC) to extrapolate edges features into salient regions.
Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
We benchmark LaPool on molecular graph prediction and understanding tasks and show that it outperforms recent GNNs.
Fast and Optimal Laplacian Solver for Gradient-Domain Image Editing using Green Function Convolution
The objective of this paper is to present a novel fast and robust method of solving the image gradient or Laplacian with minimal error, which can be used for gradient domain editing.
Novel Convolution Kernels for Computer Vision and Shape Analysis based on Electromagnetism
The objective of this paper is to present a novel convolution kernels, based on principles of electromagnetic potentials and fields, for a general use in computer vision and to demonstrate its usage for shape and stroke analysis.
Computing the Spatial Probability of Inclusion inside Partial Contours for Computer Vision Applications
Hence, it becomes possible to generate a continuous space of probability based only on the edge information, thus bridging the gap between the edge-based methods and the region-based methods.
