Explore Graph Neural Networks
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 freeWhat's a GNN?
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.
Healthcare
Disease Prediction
- RNA–disease association
- Disease–gene association
- COVID-19 spread prediction
Drug Discovery
- Protein structuring
- Protein function prediction
- Protein/drug interaction
- Drug response prediction
Medical Imaging
- Image segmentation
- Abnormality detection
- Brain connectivity research
- Surgical image analysis
Patient Risk Prediction
- Mining EHRs (health records)
Scientific Research
Particle Physics
- Particle physics simulation
Chemical Physics
- QSOR (structure-odor) modeling
Internet
Social Network Analysis
- Social influence prediction
Recommender Systems
- User and item representations
Fake News Detection
- Rumor detection
- Link classification
Identity Resolution
- Real-time personalization & advertising
Telecoms
Wireless Communication
- Power control
- Resource allocation
- Channel control
- Link scheduling
Gaming
Fraud Detection
- Collusion detection in gaming
Recommender Systems
- Online game recommendations
Finance
Fraud Detection
- Credit card, insurance, loan fraud
Trade Market Prediction
- Trader connection surveillance
Risk & Compliance
- Risk analytics
- Compliance reporting
Data Migration
- Data mapping and consolidation
Interest Rate Risk
- Risk analytics
Government
Crime Prevention
- Predicting crime associations
Fraud Detection
- Anti-money laundering & tax fraud
Contact Tracing
- Disease contact tracing
Transport
Traffic Forecasting
- Traffic speed/time prediction
Manufacturing
Bill of Materials
- 360-degree BOM analysis
Traceability
- Product recall tracing, e.g. cars
Master Data Management
- RDF graph data modeling
.svg "GNN-biotech-illustration")
Graph Neural Networks for Biotechnology
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.
