Apply now
Master'sData, AI, Simulation & Analytics Applications open

Master’s in Graph ML Engineering for Networks and Systems

Online master's programme of 1,900 hours in graph machine learning engineering for networks and systems. 12 modules covering engineering systems as graphs, classical network analysis, embeddings, graph neural networks, graph learning tasks, dynamic and spatio-temporal graphs, GNNs for communication networks and physical systems, knowledge graphs, scalability and robustness, with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

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.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Represent engineering systems as graphs.

02

Analyse networks with classical structural metrics.

03

Design graph neural networks for different tasks.

04

Model dynamic and spatio-temporal graphs.

05

Apply GNNs to communication networks and physical systems.

06

Build knowledge graphs for engineering data.

07

Deploy scalable, robust and explainable graph models.

Profile

Who it's for

  • Graph data scientists applying GNNs to real engineering networks.
  • Machine learning engineers extending their toolkit to relational data.
  • AI network engineers optimising communication and mobile networks.
  • Knowledge graph engineers integrating engineering and asset data.
  • Critical infrastructure analysts assessing network vulnerability and anomalies.
  • GNN researchers moving towards industrial applications.
  • Engineering or science graduates aiming to enter telecommunications.
Standards & tools

What you'll work with

  • ISO/IEC 39075 (GQL graph query language)
  • W3C RDF 1.1 (Resource Description Framework)
  • W3C SPARQL 1.1 (RDF query language)
  • Directive (EU) 2022/2555 (NIS2)
  • IEC 61970-301 (Common Information Model (CIM) base)
  • Regulation (EU) 2016/679 (GDPR)
  • Regulation (EU) 2024/1689 (AI Act)
  • PyTorch Geometric
  • DGL
  • NetworkX
  • Neo4j
  • igraph
Syllabus

12 modules · 1900 h

  1. 1.1Engineering systems represented as graphs
  2. 1.2Communication networks
  3. 1.3Power and water networks
  4. 1.4Transport networks
  5. 1.5Supply chains
  6. 1.6Software systems and microservices
  7. 1.7Electronic circuits as graphs
  8. 1.8Molecules and materials
  9. 1.9Choosing the representation
  10. 1.10Case study: a water network as a graph
  1. 2.1Degree and distributions
  2. 2.2Betweenness and closeness centralities
  3. 2.3PageRank and eigenvectors
  4. 2.4Communities and modularity
  5. 2.5Robustness and percolation
  6. 2.6Small-world and scale-free networks
  7. 2.7Maximum flows and minimum cuts
  8. 2.8Spectral graphs and the Laplacian
  9. 2.9NetworkX and igraph tools
  10. 2.10Lab: vulnerability analysis of a power grid
  1. 3.1Adjacency matrix factorisation
  2. 3.2DeepWalk and node2vec
  3. 3.3Knowledge graph embeddings
  4. 3.4Spectral Laplacian embeddings
  5. 3.5Evaluation of embeddings
  6. 3.6Visualisation of embeddings
  7. 3.7Dynamic node embeddings
  8. 3.8Subgraph embeddings
  9. 3.9Use in downstream tasks
  10. 3.10Practical exercise: node2vec for network anomaly detection
  1. 4.1Message passing
  2. 4.2Graph convolutional networks (GCN)
  3. 4.3GraphSAGE with inductive aggregation
  4. 4.4Graph attention networks (GAT)
  5. 4.5GIN and expressiveness
  6. 4.6Oversmoothing and depth
  7. 4.7Normalisation and regularisation
  8. 4.8Heterogeneous graphs with R-GCN
  9. 4.9Graph transformers
  10. 4.10Lab: comparison of GNN architectures
  1. 5.1Node classification
  2. 5.2Link prediction
  3. 5.3Graph classification and regression
  4. 5.4Node clustering
  5. 5.5Anomaly detection in graphs
  6. 5.6Graph generation
  7. 5.7Graph matching
  8. 5.8Self-supervised learning on graphs
  9. 5.9Evaluation and data splits
  10. 5.10Workshop: link prediction in a collaboration network
  1. 6.1Temporal graphs and events
  2. 6.2Recurrent graph networks
  3. 6.3Temporal graph networks (TGN)
  4. 6.4Spatio-temporal prediction on networks
  5. 6.5Traffic and mobility
  6. 6.6Networked sensor series
  7. 6.7Change detection in graphs
  8. 6.8Temporal scaling of models
  9. 6.9Temporal graph benchmarks
  10. 6.10Practical exercise: load prediction in a sensor network
  1. 7.1Network modelling with GNNs
  2. 7.2Delay and performance prediction
  3. 7.3RouteNet and network twins
  4. 7.4Learning-based routing
  5. 7.5Mobile network optimisation
  6. 7.6Graph-based intrusion detection
  7. 7.7Resource allocation
  8. 7.8Software-defined networking
  9. 7.9Integration into network operations
  10. 7.10Lab: delay prediction with RouteNet
  1. 8.1Optimal power flow with GNNs
  2. 8.2State estimation in power grids
  3. 8.3Water networks and leaks
  4. 8.4Physical simulation with GNNs
  5. 8.5Meshes and finite elements
  6. 8.6Fault diagnosis in systems
  7. 8.7Maintenance of networked infrastructure
  8. 8.8Physical constraints in GNNs
  9. 8.9Validation against solvers
  10. 8.10Practical exercise: load flow approximation with GNNs
  1. 9.1Ontologies and RDF
  2. 9.2Graph databases
  3. 9.3SPARQL and Cypher queries
  4. 9.4Building knowledge graphs
  5. 9.5Reasoning and completion
  6. 9.6Industrial knowledge graphs
  7. 9.7GraphRAG with language models
  8. 9.8Integration of engineering data
  9. 9.9Graph quality
  10. 9.10Workshop: asset knowledge graph with Neo4j
  1. 10.1Neighbourhood sampling
  2. 10.2Distributed GNN training
  3. 10.3Graphs with billions of edges
  4. 10.4Storage and partitioning
  5. 10.5Real-time inference
  6. 10.6PyTorch Geometric and DGL in production
  7. 10.7Vector databases and graphs
  8. 10.8Monitoring graph models
  9. 10.9Computational cost of inference
  10. 10.10Lab: scalable training with sampling
  1. 11.1Adversarial attacks on graphs
  2. 11.2Certified robustness of GNNs
  3. 11.3Explainability with GNNExplainer
  4. 11.4Fairness on graphs
  5. 11.5Privacy in graph data
  6. 11.6Graphs in critical infrastructure
  7. 11.7Cybersecurity and NIS2
  8. 11.8Validation of critical models
  9. 11.9Governance of network data
  10. 11.10Case study: explaining the alerts of a security GNN
  1. 12.1Selection of the network or system
  2. 12.2Building the graph
  3. 12.3Exploratory network analysis
  4. 12.4GNN model design
  5. 12.5Training and validation
  6. 12.6Comparison with classical methods
  7. 12.7Deployment and explainability
  8. 12.8Conclusions and applicability
  9. 12.9Master's Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training 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 the intake, so you can combine it with 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 igraph, in free, academic or evaluation versions. Practical work is based on real procedures: performance prediction in communication networks, load flow approximation in power grids and anomaly detection in infrastructure graphs. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: ISO/IEC 39075, W3C RDF 1.1, W3C SPARQL 1.1, Directive (EU) 2022/2555, IEC 61970-301, Regulation (EU) 2016/679, Regulation (EU) 2024/1689.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of ISO/IEC 39075 (GQL), W3C RDF 1.1 and W3C SPARQL 1.1 applied to real cases, not as a theoretical annex.
Industry software:PyTorch Geometric, DGL, NetworkX, Neo4j and igraph, in free, academic or evaluation versions.
Master's Thesis with defence:A graph machine learning solution for a real network or system, compared with classical methods and deployed with explainability, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Build the graph
Represent a real network or system as a graph and analyse its structure.
Benchmark classical methods
Apply centralities, embeddings and vulnerability analysis as a baseline.
Design the GNN
Compare GNN architectures and train the model for the target task.
Scale and explain
Train with sampling at scale and explain predictions with GNNExplainer.
Master's Thesis
A deployed, explainable graph ML solution compared with classical methods, defended before a panel.
Career opportunities

Where this takes you

Graph data scientistMachine learning engineerAI network engineerKnowledge graph engineerCritical infrastructure analystGNN researcher
Admissions & scholarships

Requirements

  • A university degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • An internet connection and a computer capable of running the programme's 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.

Apply now Scholarships
FAQ

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 igraph, 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 computer able to run the programme's software 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.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Master's9,970 $

Master’s in Simulation, Co-Simulation and HPC Engineering

Online master's programme of 1,900 hours in simulation, co-simulation and HPC engineering. 12 modules covering numerical methods, physical system modelling, FMI-based co-simulation, multiphysics, HPC architectures, parallel…

1900 hOnlineData, AI, Simulation & Analytics
Master's7,730 $

Master’s in Visual Analytics and Technical BI Engineering

Online master's programme of 1,900 hours in visual analytics and technical BI engineering. 12 modules covering visual analytics, perception and visual design, complex data visualisation, data…

1900 hOnlineData, AI, Simulation & Analytics
Master's8,850 $

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…

1900 hOnlineData, AI, Simulation & Analytics
Master’s in Graph ML Engineering for Networks and SystemsEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Master’s in Model and Data Observability EngineeringView programme →Master’s in Industrial Data & Platform MLOps EngineeringView programme →Master’s in Federated Learning & Privacy-Preserving ML EngineeringView programme →Master’s in Time Series, Signals and Anomaly Detection EngineeringView programme →Master’s in Digital Twins and Operations Analytics EngineeringView programme →Master’s in AI-Based Predictive Maintenance EngineeringView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.