GNNs are ideally suited for the Graphcore IPU. Learn how to deploy smarter AI applications for your industry with GNNs and get started in the cloud today.Try GNNs for free
Graph neural networks (GNNs) are AI models designed to derive insights from unstructured data described by graphs. GNNs are an ideal fit for the Graphcore IPU, designed from the ground up for AI expressed as graphs. Unlike conventional CNNs, GNNs address the challenge of working with data in irregular domains. There are many applications for GNNs including molecular analysis, drug discovery, stock market prediction, social network analysis, traffic forecasting, recommender systems in e-commerce and much more.
Graph intelligence is a rapid growth segment within AI forecast to make up a sizeable percentage of the overall AI market in the coming years. Many businesses and organizations are discovering the potential of GNNs, and are applying them in a number of areas to drive innovation within their industry.
Take data intelligence to the next level with graph neural networks for applications across drug discovery, molecular modeling, chemistry, life sciences and biotechnology.
Whether you’re working on protein sequencing or predicting patient outcomes, IPUs are designed to help you get deeper insights faster from graph neural networks.
TGN: Temporal Graph Networks is a dynamic GNN model for training on the IPU using PyTorch Geometric
GNN-based model in PyTorch Geometric developed for modelling quantum interactions between atoms in a molecule
An efficient algorithm for training deep and large Graph Convolutional Networks using PyTorch Geometric.
Graph Isomorphism Network (GIN) is used to perform graph classification for molecular property prediction using PyTorch Geometric.
Bellman-Ford networks (NBFnet) is a GNN model used for link prediction in homogeneous and heterogeneous graphs implemented in PyTorch Geometric.
A hybrid GNN/Transformer for training Molecular Property Prediction using IPUs on the PCQM4Mv2 dataset. Winner of the Open Graph Benchmark Large-Scale Challenge.
A hybrid GNN/Transformer for Molecular Property Prediction inference using IPUs trained on the PCQM4Mv2 dataset. Winner of the Open Graph Benchmark Large-Scale Challenge.
Knowledge graph embedding (KGE) for link-prediction training on IPUs using Poplar with the WikiKG90Mv2 dataset. Winner of the Open Graph Benchmark Large-Scale Challenge.
Knowledge graph embedding (KGE) for link-prediction inference on IPUs using Poplar with the WikiKG90Mv2 dataset. Winner of the Open Graph Benchmark Large-Scale Challenge.
Try IPUs in the cloud for free with a zero set-up, pre-configured Jupyter development environment on PaperspaceTry for free
Build, train and deploy your models in the cloud, using the latest IPU hardware and the frameworks you love, with our cloud service partnersBrowse providers
Have questions about installation, deployment, cloud options or any other technical queries?Get in touch
Interested in getting a quote or finding out more information about the pricing of our data centre products?Contact Sales