Ensuring data privacy and security with Federated Learning

by Michail Smyrnakis (STFC)

Monday 9 Feb 2026, 13:30 → 14:30 Europe/London

Transform (Hartree Centre)

This is the second of a series of four, AI themed, talks aimed at researchers who are interested in learning more about AI and its applications.  The talks are offered online. Registration closes 6 Feb and all participants will receive a calendar invitation. If you miss the deadline please email hartreetraining@stfc.ac.uk to be added to the calendar.

1. Concepts and practical implementation using Agentic AI tools, 29 January
2. Ensuring data privacy and security with Federated Learning, 9 February
3. Concepts and application of surrogate models for accelerating simulations and solving complex problems, 17 March
4. Fundamentals of multimodal models, 19 March

This talk introduces Federated Learning and explain how it enables machine learning models to be trained across decentralised devices. Participants will learn how this approach addresses privacy concerns, with practical applications in healthcare, finance, and other sensitive domains. The session will focus on the following elements 

• what federated learning is and identify scenarios where it is preferable to centralised training.
• common federated learning topologies (centralized, hierarchical, ring, peer-to-peer, tree, mesh and articulate their trade-offs in scalability, robustness, and communication cost.
• Understand the impact of data heterogeneity (non-IID data) on convergence and model performance in federated systems.

Materials, including video recordings, will be made available after the event via the Hartree Centre Training Portal