Master’s in Graph ML for Networks and Systems
Online master's programme of 1,900 hours in graph machine learning for networks and systems: GNNs for power grids, traffic, supply chains and cybersecurity. 12 modules covering graphs and networked systems, classical network analysis, embeddings, graph neural networks, graph learning tasks, spatio-temporal graphs, applications in power grids, telecoms and supply chains, scaling and deployment, and robustness and explainability, with an assigned technical tutor.
Master’s in Graph ML for Networks and Systems — studying from New Zealand
New Zealand's data and artificial intelligence sector is growing, with strong activity in Auckland, Wellington and Christchurch across fintech, agritech, health analytics and government data services. Universities including the University of Auckland, the University of Otago and Victoria University of Wellington run leading research in machine learning and computational modelling. Simulation and analytics skills are widely applied in agriculture, energy and environmental modelling, and employers include government agencies such as Stats NZ as well as technology firms and consultancies.
Fees for New Zealand: NZ$17,700 (New Zealand dollar), with instalments and employer sponsorship available.
Relevant bodies in New Zealand
Typical roles
Questions from New Zealand
Are data and AI engineering roles regulated in New Zealand, and how does that affect a private qualification?
Data and AI are not regulated professional titles in New Zealand, though privacy obligations fall under the Office of the Privacy Commissioner. Engineers who want chartered status can pursue registration through Engineering New Zealand. SEIUM's qualifications are private, not state degrees, and not accredited by a national body, so employers decide how much they value them.
Which New Zealand employers hire data, AI and simulation engineers?
Demand is found in banks and insurers, government agencies, healthcare, energy and utilities, technology firms, and consultancies. Employers usually assess portfolios, practical projects and technical interviews more than credentials. A private online programme can help build relevant skills, but it does not guarantee a position or a specific salary.
Can I complete this online from New Zealand in English while working?
Yes. The programmes are fully online and taught in English, so you can study from New Zealand without a student visa. You will have an assigned technical tutor and complete a final project. Specialist courses are 300 hours, diplomas 800 and master's 1,900. Fees can be paid in instalments, and some employers sponsor study, so ask yours early.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Represent engineering systems as graphs and analyse their structure.
Learn vector representations of nodes, links and graphs.
Design and train graph neural networks.
Model spatio-temporal phenomena on networks.
Apply GNNs to power, telecommunications and supply networks.
Scale and deploy graph models in production.
Assess the robustness and explainability of network models.
Who it's for
- Graph machine learning engineers.
- Network data scientists.
- Power grid analytics engineers.
- Telecommunications optimisation specialists.
- Supply chain risk analysts.
- Geometric AI researchers.
- Engineering or science graduates looking to enter the power grid sector.
What you'll work with
- ISO/IEC 39075 (GQL) (graph query language)
- IEC 61970 (CIM) (common information model for energy management)
- Regulation (EU) 2024/1689 (AI Act)
- Directive (EU) 2022/2557 (resilience of critical entities)
- ISO/IEC 22989 (AI concepts and terminology)
- ISO/IEC 23053 (framework for AI systems using machine learning)
- PyTorch Geometric
- DGL
- NetworkX
- Neo4j
- pandapower
12 modules
1.1Graph theory applied to engineering1.2Directed, weighted graphs and multigraphs1.3Heterogeneous and knowledge graphs1.4Dynamic and temporal graphs1.5Power, water and transport networks1.6Communication and supply networks1.7Representations: matrices and lists1.8Structural properties and scale-free networks1.9Topology data sources1.10Case study: modelling a distribution network as a graph
2.1Degree, betweenness and eigenvector centrality2.2PageRank and its variants2.3Community detection2.4Shortest paths and maximum flows2.5Robustness and percolation2.6Vulnerability analysis2.7Motifs and subgraphs2.8Node similarity metrics2.9Visualising large graphs2.10Lab: robustness analysis with NetworkX
3.1Spectral graph theory3.2The Laplacian and its decomposition3.3DeepWalk and node2vec3.4TransE knowledge graph embeddings3.5Encoding node and edge attributes3.6Embeddings for dynamic graphs3.7Dimensionality reduction3.8Evaluating embeddings3.9Scalability of representation learning3.10Practical exercise: embeddings of a transport network
4.1The message-passing paradigm4.2GCN and spectral convolutions4.3GraphSAGE and inductive learning4.4GAT attention networks4.5Graph Isomorphism Network4.6Over-smoothing and depth4.7Pooling and readout4.8Heterogeneous graphs with R-GCN4.9Expressiveness and the Weisfeiler-Lehman test4.10Lab: GNN with PyTorch Geometric
5.1Node classification5.2Link prediction5.3Graph classification and regression5.4Semi-supervised learning5.5Anomaly detection on graphs5.6Self-supervised and contrastive learning5.7Graph generation5.8Graph-based recommendation5.9Evaluation metrics and splits5.10Practical exercise: link failure prediction
6.1Time series on graphs6.2STGCN and DCRNN6.3Traffic forecasting6.4Load forecasting in power grids6.5Spatio-temporal attention6.6Graphs with changing topology6.7Imputation of networked sensors6.8Propagation models6.9Uncertainty in forecasts6.10Lab: traffic forecasting with sensor data
7.1State estimation with GNNs7.2Approximate power flow7.3Fault location7.4Distribution network reconfiguration7.5Integration of renewables7.6False data injection attacks7.7IEEE test case data7.8Physical constraints in learning7.9Validation against classical solvers7.10Case study: GNN power flow on the IEEE 118-bus case
8.1Modelling IP networks as graphs8.2Latency prediction with RouteNet8.3Learning-assisted routing8.4Software-defined network management8.5Intrusion detection in traffic8.6Mobile network planning8.7Radio resource optimisation8.8Network digital twins8.9Integration with orchestrators8.10Workshop: performance model of a network
9.1Multi-tier supply networks9.2Risk propagation9.3Particle simulation with GNNs9.4Finite element meshes as graphs9.5Pipe networks and leaks9.6Manufacturing process graphs9.7Asset knowledge graphs9.8Graphs from P&ID diagrams9.9Dependency-based maintenance9.10Practical exercise: risk in a supplier network
10.1Neighbourhood sampling10.2Distributed training with DGL10.3Neo4j graph databases10.4Cypher and GQL queries10.5Real-time inference10.6Graph pipelines in production10.7Monitoring graph models10.8Hardware and memory10.9Integration with SCADA systems10.10Lab: GNN served on a graph database
11.1Adversarial attacks on graphs11.2Certified robustness11.3GNNExplainer and explanations11.4Uncertainty and calibration11.5Fairness in social graphs11.6Privacy in graphs11.7AI regulation in critical infrastructure11.8Documentation and auditing11.9Validation with network experts11.10Case study: explaining a failure prediction
12.1Selection of the network and problem12.2Graph construction and data12.3Initial structural analysis12.4Model design12.5Training and tuning12.6Evaluation against baselines12.7Explainability and robustness12.8Deployment plan12.9Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
The programme is delivered 100% online on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so it fits around your job.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is PyTorch Geometric, DGL, NetworkX, Neo4j and pandapower, in free, academic or evaluation versions. Exercises are based on real procedures: benchmarks on IEEE network cases, forecasting with real sensor data and robustness analysis against simulated failures. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: ISO/IEC 39075 (GQL), IEC 61970 (CIM), Regulation (EU) 2024/1689, Directive (EU) 2022/2557, ISO/IEC 22989, ISO/IEC 23053.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
- Internet connection and a computer capable of running the programme software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with PyTorch Geometric, DGL, NetworkX, Neo4j and pandapower, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.
A university degree in engineering, science or architecture (or equivalent professional experience), a suitable computer and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Master’s in Privacy, Federated and Graph Engineering
Online master's programme of 1,900 hours in privacy engineering, federated learning and graphs. 12 modules covering privacy in data systems, anonymisation, differential privacy, cryptography for learning,…
Master’s in Model Verification, Validation and UQ Engineering
Online master's programme of 1,900 hours in model verification, validation and uncertainty quantification (UQ) engineering. 12 modules covering model credibility, code and solution verification, uncertainty propagation,…
Master’s in Optimisation and OR for Engineering
Online master's programme of 1,900 hours in optimisation and operations research for engineering: 12 modules covering linear and integer optimisation, design optimisation, process optimisation, industrial planning…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships