Programme

Sign in to build your own agenda. Sign in

1. 08:30
   Registration and coffee · 08:30–09:00
2. 09:00
   09:00–09:30· Aula· Ceremony

   Opening

   Speaker: Eleni Markou, general chair

3. 09:30
   09:30–10:30· Aula· Keynote

   Keynote: Privacy is a systems problem

   Speaker: Prof. Helena Varga (fictional)

4. 10:30
   Coffee break · 10:30–11:00
5. 11:00
   11:00–12:30· Aula· Paper session· Federated and privacy-preserving learning

   Federated learning I

   Chair: Anna Kowalska

   1. Asynchronous buffered aggregation for federated learning on heterogeneous edge fleets
      Lucas Meyer (presenting), Ana Costa
   2. What does a trusted aggregation server cost? Measuring privacy overheads in federated forecasting
      Oskar Lindqvist (presenting), Irene Galanis, Pablo Moreno
   3. Forgetting on request: certified machine unlearning for federated recommender systems
      Katerina Vlachou (presenting), Felix Brandt, Sara Romano

   11:00–12:30· Room A· Paper session· Trustworthy and explainable AI

   Trustworthy AI I

   Chair: Mateo Silva

   1. Explanations that clinicians use: a field study of feature attributions in triage
      Theo Laurent (presenting), Iris Andreou
   2. Auditing hiring classifiers for intersectional bias with limited demographic data
      Viktor Ivanov
   3. Mapping the EU AI Act's human oversight requirement to concrete interface patterns
      Irene Galanis (presenting), Pablo Moreno
6. 12:30
   Lunch · 12:30–14:00
7. 14:00
   14:00–15:00· Room A· Paper session· AI at the edge

   AI at the edge

   Chair: Ingrid Lund

   1. On-device training of TabNet models on Raspberry Pi 5: memory, time and energy
      Maya Dimou (presenting), Nikolai Sokolov
   2. Quantisation-aware federated training for microcontrollers
      Luca Greco (presenting), Alma Hansen, Theo Laurent

   14:00–15:00· Room B· Paper session· Trustworthy and explainable AI

   Trustworthy AI II

   Chair: Anna Kowalska

   1. Do counterfactual explanations survive model updates?
      Felix Brandt (presenting), Sara Romano
   2. Measuring hallucination in retrieval-augmented assistants for public administration
      Lina Weber (presenting), Arjun Mehta, Clara Fischer
8. 15:30
   Coffee break · 15:30–16:00
9. 16:00
   16:00–17:30· Aula· Panel

   Panel: Human oversight in practice

   Speaker: Moderated by Dimitris Alexiou

10. 19:00
    19:00–21:00· Social event

    Welcome reception