<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=145304570664993&amp;ev=PageView&amp;noscript=1">

91视频APP

Skip to content

Graph Neural Networks with IPU

GNNs are ideally suited for the 91视频APP IPU architecture. Get started today with a wide range of GNN applications for your industry or your scientific research with GNNs .

Try GNNs today

GNNs for finance, life sciences, smart cities and more

Graph neural networks (GNNs) are AI models designed to derive insights from unstructured data described by graphs. GNNs are an ideal fit for the 91视频APP 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, fraud detection, stock market prediction, traffic forecasting and much more. 

HO鈥屸�嶁�屸�峎 GNNS A鈥峈鈥嶁�屸�岴 A鈥嶁�孋鈥嶁�岰鈥孍LER鈥屸�岮鈥孴ING鈥屸�� YO鈥屸�屸�峌鈥孯鈥� IND鈥孶鈥嶁�峉TR鈥孻

Graph intelligence is a rapid growth segment, forecast to make up a sizeable percentage of the overall AI market in the coming years. Many businesses and organisations are discovering the potential of GNNs, and are applying them in a number of areas to drive innovation within their industry.

Healthcare

Disease

Disease Prediction

  • RNA鈥揹isease association
  • Disease鈥揼ene association
  • COVID-19 spread prediction
Syringe

Drug Discovery

  • Protein structuring
  • Protein function prediction
  • Protein/drug interaction
  • Drug response prediction
X-ray

Medical Imaging

  • Image segmentation
  • Abnormality detection
  • Brain connectivity research
  • Surgical image analysis
Heart

Patient Risk Prediction

  • Mining EHRs (health records)

Scientific Research

Particle Physics

Particle Physics

  • Particle physics simulation
Chemical Physics

Chemical Physics

  • QSOR (structure-odor) modeling

Internet

Social

Social Network Analysis

  • Social influence prediction
Thumbsup

Recommender Systems

  • User and item representations
Megaphone

Fake News Detection

  • Rumor detection
  • Link classification
Magnet

Identity Resolution

  • Real-time personalization & advertising 

Telecoms

Wireless

Wireless Communication

  • Power control
  • Resource allocation鈥�
  • Channel control鈥�
  • Link scheduling

Gaming

GamePad

Fraud Detection

  • Collusion detection in gaming
Thumbsup

Recommender Systems

  • Online game recommendations

Finance

Fraud-1

Fraud Detection

  • Credit card, insurance, loan fraud
Line Graph_1

Trade Market Prediction

  • Trader connection surveillance
Warning

Risk & Compliance

  • Risk analytics
  • Compliance reporting
Storage

Data Migration

  • Data mapping and consolidation
Interest

Interest Rate Risk

  • Risk analytics

Government

Handcuffs

Crime Prevention

  • Predicting crime associations
Fraud-1

Fraud Detection

  • Anti-money laundering & tax fraud
Magnifier

Contact Tracing

  • Disease contact tracing

Transport

Traffic

Traffic Forecasting

  • Traffic speed/time prediction

Manufacturing

CheckList

Bill of Materials

  • 360-degree BOM analysis
Magnifier

Traceability

  • Product recall tracing, e.g. cars
Storage

Master Data Management

  • RDF graph data modelling
GNN-biotech-illustration

Graph Neural Networks for Biotech & life science

Whether you鈥檙e working on protein sequencing, molecular modelling, computational chemistry or drug discovery, IPUs are designed to help you get deeper insights faster from graph neural networks.

Developed with Valence & Mila, Graphium is an open-source library designed for graph representation learning on real-world chemistry tasks.

Find out more

Explore our GNN models, READY-MADE For IPU

TGN Training

TGN: Temporal Graph Networks is a dynamic GNN model for training on the IPU using PyG (PyTorch Geometric)

RGCN Training

Training a GNN to do Fraud Detection using Relational Graph Convolution Network (RGCN) on IPUs with PyG (PyTorch Geometric)

SchNet Training

GNN-based model in PyG (PyTorch Geometric) developed for modelling quantum interactions between atoms in a molecule

Cluster-GCN Training

An efficient algorithm for training deep and large Graph Convolutional Networks using PyG (PyTorch Geometric)

GIN Training

Graph Isomorphism Network (GIN) is used to perform graph classification for molecular property prediction using PyG (PyTorch Geometric)

Bellman-Ford networks (NBFnet)

Bellman-Ford networks (NBFnet) is a GNN model used for link prediction in homogeneous and heterogeneous graphs implemented in PyG (PyTorch Geometric)

GPS++ Training

A hybrid GNN/Transformer for training Molecular Property Prediction using IPUs on the PCQM4Mv2 dataset. Winner of the Open Graph Benchmark Large-Scale Challenge.

GPS++ Inference

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.

Distributed KGE - TransE (256) Training

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.

Distributed KGE - TransE (256) Inference

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.

GNN Resources

Ready to get started?

FIND鈥� A C鈥屸�峀O鈥屸�峌鈥岲鈥� P鈥峈鈥孫鈥峍ID鈥孍R鈥�

Build, train and deploy your models in the cloud, using the latest IPU hardware and the frameworks you love, with our cloud service partners

Browse providers

SP鈥孍AK TO鈥� AN AI EXP鈥孍R鈥孴

Have questions about installation, deployment, cloud options or any other technical queries?

Get in touch

GET A Q鈥峌OTE + P鈥孯IC鈥屸�岻NG鈥屸��

Interested in getting a quote or finding out more information about the pricing of our data centre products?

Contact Sales