WHAT IS FEDERATED LEARNING?
Federated Learning is a decentralised and privacy-friendly form of machine learning. This means that there is no need for a central database to hold all of the sensitive data, so these data cannot be leaked. Instead of bringing the data to the machine learning model, Federated Learning brings the machine learning model to the data.
In this way, the training of the models is broken down into sub-calculations that are performed locally at an organisation. After carrying out the calculations, only the anonymised (intermediate) results are shared with the organisations conducting the research, not the privacy-sensitive data itself.
“FINALLY, A PRIVACY-FRIENDLY WAY TO HARNESS DATA” WHITEPAPER
Discover how you can use data without violating privacy
WHICH PROBLEMS DOES FEDERATED LEARNING SOLVE?
Federated Learning solves two major problems of data analysis: improved qualitative analyses for society and safeguarding of citizens’ rights in relation to privacy.
These days, analysing large amounts of data is easier than ever before. Computing power is increasing and algorithms are becoming ever more advanced. Although more and more data is available for valuable analyses, there are an increasing number of societal objections to the use of sensitive data.
WHAT CAN ORGANISATIONS GAIN FROM FEDERATED LEARNING?
Federated Learning allows you to harness data without violating privacy. The amount of available data is greater as you can analyse data from multiple databases. In turn, the results of a study are more reliable. This means better predictions and better models, leading to much more informed (policy) decisions.
An example? Take cancer research. With Federated Learning, you can analyse anonymised data on things like successful treatment methods for each type of cancer in different people across all hospitals without violating patient privacy.
WHAT DOES TNO DO IN THE FIELD OF FEDERATED LEARNING AND HOW CAN YOU WORK WITH TNO?

HELPING TO PREVENT DIABETES
No less than 8.5% of the world’s population has diabetes, 90% of which is Type 2. This is particularly distressing as it can often be prevented by different lifestyle choices, for example.
How can machine learning (ML) help? By identifying risk groups and warning them as early as possible, i.e. before Type 2 develops. To do that, the ML model needs to be trained as well as possible on a large number of people with different lifestyles and medical conditions in multiple age groups.
To do this properly, you need many different data sources from healthcare institutions. However, medical data is so well protected under the GDPR that sharing is almost impossible – let alone storing all that sensitive data in a central database to run models on it.
HOW FEDERATED LEARNING CONTRIBUTES
TNO has collaborated with the organisation Lifelines to create a Federated Logistic Regression model to predict the emergence of Type 2 diabetes for people aged between two and eleven. Via Lifelines, data from 167,000 people in the Netherlands were analysed in a privacy-friendly manner.
The data comes from various sources, including data from proteins tested in the lab and surveys of people regarding their lifestyle. This resulted in a Federated Learning model that works almost as well as a globally trained model. The results are promising and justify further research.

PREDICTING A NEIGHBOURHOOD’S ENERGY DEMAND
The energy transition is already a huge topic and will only grow larger in the coming years. An important issue is predicting energy demand in order to match supply and demand.
You have to know how much grid capacity is needed in order to be able to deliver a supply that matches the energy demand, preferably per neighbourhood so that smart supply can be implemented. But requesting your energy consumption is difficult. It can cause privacy issues, like a third party may know when you are not at home.
HOW FEDERATED LEARNING CONTRIBUTES
Together with partners like Strukton, TNO has been working on a model for predicting a neighbourhood’s energy demand. This is done in a privacy-friendly manner using Federated Learning. This means that the personal data of households do not have to be viewed by researchers or stored at a central location, thereby preventing loss of privacy.
Instead, the energy demand per neighbourhood can now be analysed and predicted in a privacy-friendly manner. On this basis, it can be determined how much capacity is needed. What a result! With the help of FL, the energy demand of a neighbourhood can be predicted without violating the privacy of citizens and with the aim of guaranteeing a stable electricity supply.
GETTING STARTED WITH PRIVACY-FRIENDLY DATA
Wondering how you can join us in using Federated Learning to harness data in a privacy-friendly way? Please get in touch.
How you can harness data in a privacy-friendly way
Envision it: better treatment methods for patients by learning from the successes and failures of doctors and pharmaceutical companies. Detecting money laundering activities by bringing together data from... Read morePrivacy by design: combining data for better government services
The government works with a great deal of data from citizens and businesses. It has a legal duty to carefully secure these data in order to protect everyone’s privacy, but the government is also always... Read moreMPC as a fraud detection and anti-money laundering (AML) tool
Fraud, money laundering and other financial and economic crimes are difficult to combat. Every year, millions of citizens and thousands of businesses in the EU fall victim to fraud. Money laundering is also how... Read more- Artificial Intelligence
- Application areas
- Use cases
- Program line 1: Safe autonomous systems in an open world
- Program line 2: Responsible human-machine interaction
- Secure learning in money laundering detection
- Fair decision making in the job market
- Secure learning in diabetes-2 advice
- Diagnosing for printer maintenance
- Subsidence monitoring
- Fair decision making in justice
- Augmented worker for smart industry
- Energy balancing for smart homes
- Secure learning in oncology research
- Innovation monitoring in policy
- News
- Defence, Safety & Security
- Roadmaps
- Operations & Human Factors
- Climate Chambers for Research into Human Performance
- Desdemona: The ultimate motion simulator
- LT Lab: the TNO learning technology laboratory
- Performance and health monitoring
- Motion sickness and performance
- The neurobiology of Stress
- NetForce Command: an alternative to hierarchical command and control
- Operational military performance in a virtual world
- SUPRA
- Simulation Live Virtual and Constructive
- Concept Development & Experimentation
- IAMD: Integrated Air & Missile Defence
- JROADS
- FACSIM
- Helicopter studies
- Replacement of the F-16
- MARVEL / Comprehensive Approach
- TNO ACE: Advanced CD&E Environment
- Integrated approach to Dutch Royal Navy patrol ships
- Operational analysis during military operations
- SketchaWorld: from sketch to virtual world
- Camouflage
- Information & Sensor Systems
- Digital Resilience of The Netherlands
- LFAS - Low Frequency Active Sonar
- Tanker Remote Vision System
- Platform signatures
- TNO shapes the future of MMICs and RFICs
- CARPET: Computer-Aided Radar Performance Evaluation Tool
- Underwater Warfare and Security
- Wide Area Motion Imagery WAMI
- SAKAMATA: sonar and marine mammals
- PARANOID: rapid information processing
- Mine analysis and threat evaluation
- Ship acoustics and underwater acoustic signatures
- PERSEUS Wind Turbine Radar Interference Assessment tool
- Electromagnetic security
- Operating safely at sea
- Operations at sea
- Ocean Space
- National Security
- A new vision on modernizing the emergency reporting process
- Social media in the security sector
- Automatic Video Compilation and Analysis System (AVACS)
- The Dutch Cyber Cube Method: Improving Human Capital for SOCs and CSIRTs
- Concealed weapon detection
- FP7 Project IMPACT Europe
- Critical Infrastructure Protection (CIP) policies in Europe
- @MIGO: border control
- Smarter Surveillance, man, machine, synergy
- Cyber Security of Industrial Control Systems
- Privacy enhancing techniques in cyber security data sharing
- Driving Innovation in Crisis Management with DRIVER+
- Crisis management: new challenges, new opportunities
- The learning professional: resilient and deployable for the long term
- Protection, Munitions & Weapons
- Weapons systems control and analysis
- Weapon Effects & Protection Center
- Firepower
- Protection and survivability of vehicles
- Naval protection and survivability
- Infrastructure protection and survivability
- World-class ballistics research
- Countering Explosive Threats
- Materials for protection concepts
- Processing of Propellants, Explosives and Pyrotechnics
- Ammunition Safety
- Ballistic Performance and Personal Protection
- Chemical, Biological, Radiological and Nuclear (CBRN) Protection
- Anticipating accidents, incidents and threats
- Protecting those who protect us
- Process Safety Solutions: Expertise in Handling Hazardous Conditions Safely
- Expertise groups
- Acoustics and Sonar
- Chemical, Biological, Radiological and Nuclear (CBRN) Protection
- Electronic Defence
- Energetic Materials
- Explosions, Ballistics and Protection
- Human Behaviour and Organisational Innovation
- Human Machine Teaming
- Human Performance
- Intelligent Autonomous Systems
- Intelligent Imaging
- Military Operations
- Modelling, Simulation and Gaming
- Networked Organisations
- Radar Technology
- Weapon Systems
- Energy Transition
- Roadmaps
- Renewable electricity
- Towards large-scale generation of wind energy
- The important of support structures
- Wind turbines, fully in motion
- Innovation towards 10-20 MW offshore wind turbines
- Modeling 10MW+ turbines aerodynamically
- Design for Reliable Power Performance (D4REL)
- Optimised wind blade tip design
- Vortex-wake models in wind turbine design
- Modelling improvement wind turbine blades
- Converters for Clean, Low Cost Electricity
- Haliade X: largest wind turbine ever
- New research on blade tip improvements
- Less production per wind turbine, still higher yield
- Logistics innovative strength at home and abroad
- Wind turbine management and maintenance
- Wind farms in synergy with the environment
- Innovative methods for wind measurements
- Keeping the electricity grid stable when there’s a surplus of wind and solar
- Innovation and the rise of solar energy
- Solar farms respecting landscape and nature
- Solar panels on farmland
- Research innovative solar parks
- Better design of solar parks
- Savings on solar farm operations and maintenance
- Floating solar panels on inland waterbodies
- Offshore solar energy
- National Consortium Solar in Landscape
- National Consortium Solar on Water
- Field lab floating solar
- Research into environmental effects of solar, wind energy
- Solar energy on buildings and infrastructure
- Solar panels in façades
- Solar windows
- More focus on safety of solar systems
- Solar heat and PV-T
- Roofs for solar energy
- Noise barriers producing solar energy
- Solar energy in road surfaces and crash barriers
- Solar panel energy generated on dikes
- Solar and infrastructure
- Outdoor test facility for BIPV(T)
- Solar Highways
- Solar-powered cars
- Mass customization
- Solar panel efficiency
- New technologies make PV more versatile
- Webinar: Innovations in solar energy technologies
- Putting Europe back in the lead in solar panel production
- System transition
- The social aspects of the energy transition
- TNO facilities for research into environmental effects of solar and wind energy
- Effective interventions to increase energy efficiency and reduce energy poverty
- Green and Ease under one roof
- Capacity building programme for energy efficiency in industry
- Zooming in on the future to make the right choices
- Scenarios for a climate-neutral energy system
- A fair system without energy poverty
- Financing the energy transition
- LAUNCH
- Successful neighbourhood approach: motivate residents
- Towards a reliable, affordable and fair energy system
- Towards CO2 neutral industry
- Reducing CO2 emissions through capture, use and storage
- SEWGS: revolutionary CO2-reduction technology and blue hydrogen production
- STEPWISE and FReSMe: CO2 reduction solutions for the steel industry
- 3D-printing for CO2 capture productivity increase
- Multi-partner ALIGN-CCUS project
- CEMCAP
- Reduce emissions steel industry
- CO₂ capture with AVR
- On-site CO₂ Capture Services: reducing emissions cost effectively
- SEDMES: Efficient technology to convert CO2 to useful product
- Hydrogen for a sustainable energy supply
- Optimising production hydrogen
- Hydrogen storage and transport
- Hydrogen, fuel and feedstock
- H-vision: blue hydrogen to accelerate carbon-low industry
- 15 things you need to know about hydrogen
- World first: Green hydrogen production in the North Sea
- New research centre for hydrogen production
- Identifying the future international chain of green hydrogen
- Opportunities for green hydrogen for the manufacturing industry investigated
- Hydrogen from offshore wind: optimising the electricity grid
- Faraday lab: optimising and scaling up electrolysis
- Blue hydrogen paves the way for green hydrogen
- Biomass to fuels and feedstock
- ARBAHEAT - Sustainable future for coal-fired power stations possible through conversion to biomass
- AMBITION Advanced biofuel production from lignin rich residues
- BECOOL EU Brazilian cooperation on advanced biofuels
- Horti-BlueC - a new EU cooperation on reducing Bio-waste and CO2-footprint in horticulture
- UNRAVEL - valorization of lignocellulosic biomass
- MacroFuels advanced biofuels from seaweed
- BRISK2 Biofuel Research Infrastructure for Sharing Knowledge
- New facility for seaweed processing
- TORWASH technology successful for waste water treatment and recycling plastics
- Biofuels lab: Making transport more sustainable with biofuels
- Take-Off: Sustainable aviation fuels from CO2, water and green energy
- HEREWEAR: Circular textiles from locally-sourced bio-based materials
- Transition to e-fuels: a strategy for HIC Rotterdam
- Re-use of existing infrastructure to accelerate the energy transition
- Sustainable Industrial Heat System
- 4 pioneering routes to a CO2 neutral industry
- Research facility Industrial Electrification accelerates greening of Rotterdam port
- Mollier facility: innovating in industrial drying technology
- Research facility for negative CO2 emissions
- Carnot lab accelerates sustainable industrial heat management
- Using energy and raw materials efficiently in industry
- e-Missi0n MOOI: TNO supports Dow and Shell in electric cracking
- CO2 reduction requires improvement of industrial processes
- Making the industrial energy transition feasible and affordable
- Sustainable subsurface
- Geological Survey of the Netherlands
- Geological Survey of the Netherlands
- 100 years of geological mapping
- GeoTOP
- Sand, gravel and clay extraction
- GIS and other tools for interactive planning
- DINO, Data and Information of the Dutch Subsurface
- BRO: the Dutch Key Register of the Subsurface
- Sustainable use and management Flemish-Dutch subsurface
- Petroleum Geological Atlas of the Southern Permian Basin
- 3D Subsurface mapping of the Dutch offshore
- Geological Survey of the Netherlands across borders
- Towards an energy-producing environment
- Expertise
- Industry
- Roadmaps
- Flexible & Free-form Products
- Space & Scientific Instrumentation
- Semiconductor Equipment
- Smart Industry
- Expertise groups
- Buildings, Infrastructure & Maritime
- Roadmaps
- Safe and Sustainable Living Environment
- Infrastructure
- Sustainable buildings: towards an energy-producing built environment
- Building innovation
- Greenhouse design
- Digitisation in construction
- Smart megastructures
- Expertise groups
- Circular Economy & Environment
- Roadmaps
- Circular economy
- Environment & Climate
- Sustainable Chemical Industry
- Expertise groups
- Healthy Living
- Roadmaps
- Health Technology & Digital Health
- Biomedical Health
- Work
- Youth
- Expertise groups
- Traffic & Transport
- Roadmaps
- SMART and Safe Traffic and Transport
- Societal impact for accessibility and liveability
- Decision-making information based on facts for municipalities
- Making disruptive technologies practicable
- Accessible, healthy and vibrant cities
- CITYkeys – Performance evaluation framework for smart cities and projects
- Big data ecosystems: collaborating on data-controlled cities
- Knowledge mediator puts an end to bickering
- Intact – Climate resilient critical infrastructure
- Organising mobility
- Smart mobility and logistics
- Smart vehicles
- Smart Mobility Research Centre SMRC
- Sustainable Traffic and Transport
- Sustainable Mobility and Logistics
- Improving air quality by monitoring real-world emissions
- Emission factors for road traffic
- Measuring the emissions of powered two wheelers
- Emissions of particulate matter from diesel cars
- Random Cycle Generator
- EnViVer: model traffic flow and emissions
- Measuring real-world emissions with TNO’s Smart Emissions Measurement System (SEMS)
- Measuring the emissions of trucks and buses
- Reducing Greenhouse Gas Emissions in Commercial Road Transport
- Measuring the emissions of non-road mobile machinery
- Emission measures in practice
- The transition to CO2-neutral mobility in 2050
- Sustainable Vehicles
- Innovative technologies for zero-emission vehicles
- CO2 reduction by high-efficiency Flex Fuel technology with extremely low emissions
- Actual energy consumption and emissions
- Automotive Battery Research
- Making transport more sustainable by means of electric vehicles
- Energy Efficient Electric Bus E3Bus
- eCoMove
- How hydrogen can accelerate energy transition in the transport sector
- Green performance of ships
- Expertise groups
- Information & Communication Technology
- Roadmaps
- Fast open infrastructures
- Data sharing
- Trusted ICT
- Efficiency, effectiveness, quality and the costs of systems
- Expertise groups
- Strategic Analysis & Policy
- Expertise groups
- Strategic Business Analysis
- Strategy & Policy
- Orchestrating Innovation
- Tech Transfer
Madelon Molhoek MSc
- Hybrid AI
- Responsible AI
- Datascience
Send a question to Madelon Molhoek MSc
Your question has been sent.
Sorry! Something unexpected happened. Please try again later.