Swiss Institute of Bioinformatics @CERN

Monday 12 Oct 2026, 09:45 → 13:15 Europe/Zurich

61/1-017 - Room D (CERN)

09:45 → 10:00 Arrival at CERN

meet at CERN reception, in front of tram 18 stop

10:00 → 10:30 Introduction to KT, CAFEIN in particular

CAFEIN is a machine learning platform designed for accessible, flexible, scalable, and privacy-preserving workflows. Born at CERN to meet the data challenges of particle physics and accelerator science, CAFEIN now drives innovation in healthcare, industrial maintenance, and international collaborations.

Speaker: Luigi Serio (CERN)

CAFEIN- CERN's federated learning and data analytics platform October 2026.pdf

CAFEIN- CERN's federated learning and data analytics platform October 2026.pptx

few references:

1. arXiv:2605.13418  [pdf, ps, other] 

   cs.LG

   DP-KFC: Data-Free Preconditioning for Privacy-Preserving Deep Learning

   Authors: Marc Molina Van den Bosch, Riccardo Taiello, Albert Sund Aillet, Andrea Protani, Miguel Angel Gonzalez Ballester, Luigi Serio

   Abstract: Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD injects isotropic noise. Second-order preconditioning can resolve this, but estimating curvature typically requires private data (consuming privacy budget) or public data (introducing distribution shift). We show that the Fisher Information Matrix dec… ▽ More

   Submitted 13 May, 2026; originally announced May 2026.

   Comments: Accepted at the International Conference on Machine Learning (ICML 2026). 9 pages main text + appendix, 5 figures, 2 tables. Code: https://github.com/molinamarcvdb/DP-KFC

2. arXiv:2601.15042  [pdf, ps, other] 

   cs.CV cs.AI

   Federated Transformer-GNN for Privacy-Preserving Brain Tumor Localization with Modality-Level Explainability

   Authors: Andrea Protani, Riccardo Taiello, Marc Molina Van Den Bosch, Luigi Serio

   Abstract: Deep learning models for brain tumor analysis require large and diverse datasets that are often siloed across healthcare institutions due to privacy regulations. We present a federated learning framework for brain tumor localization that enables multi-institutional collaboration without sharing sensitive patient data. Our method extends a hybrid Transformer-Graph Neural Network architecture derive… ▽ More

   Submitted 21 January, 2026; originally announced January 2026.

3. arXiv:2601.14055  [pdf, ps, other] 

   cs.CV cs.AI

   Decoder-Free Supervoxel GNN for Accurate Brain-Tumor Localization in Multi-Modal MRI

   Authors: Andrea Protani, Marc Molina Van Den Bosch, Lorenzo Giusti, Heloisa Barbosa Da Silva, Paolo Cacace, Albert Sund Aillet, Miguel Angel Gonzalez Ballester, Friedhelm Hummel, Luigi Serio

   Abstract: Modern vision backbones for 3D medical imaging typically process dense voxel grids through parameter-heavy encoder-decoder structures, a design that allocates a significant portion of its parameters to spatial reconstruction rather than feature learning. Our approach introduces SVGFormer, a decoder-free pipeline built upon a content-aware grouping stage that partitions the volume into a semantic g… ▽ More

   Submitted 20 January, 2026; originally announced January 2026.

   Comments: 10 pages, 3 figures,

4. arXiv:2509.20175  [pdf, ps, other] 

   cs.AI cs.CL

   Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI

   Authors: Lorenzo Giusti, Ole Anton Werner, Riccardo Taiello, Matilde Carvalho Costa, Emre Tosun, Andrea Protani, Marc Molina, Rodrigo Lopes de Almeida, Paolo Cacace, Diogo Reis Santos, Luigi Serio

   Abstract: We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable profiles that make agent capabilities searchable through semantic embeddings, enabling agents to advertise their capabilities, cost, and limitations. Our aarch… ▽ More

   Submitted 24 September, 2025; originally announced September 2025.

   Comments: 18 pages, 4 figures

    

    

5. arXiv:2411.02286  [pdf, other] 

   cs.LG cs.AI eess.SP

   Federated GNNs for EEG-Based Stroke Assessment

   Authors: Andrea Protani, Lorenzo Giusti, Albert Sund Aillet, Chiara Iacovelli, Giuseppe Reale, Simona Sacco, Paolo Manganotti, Lucio Marinelli, Diogo Reis Santos, Pierpaolo Brutti, Pietro Caliandro, Luigi Serio

   Abstract: Machine learning (ML) has the potential to become an essential tool in supporting clinical decision-making processes, offering enhanced diagnostic capabilities and personalized treatment plans. However, outsourcing medical records to train ML models using patient data raises legal, privacy, and security concerns. Federated learning has emerged as a promising paradigm for collaborative ML, meeting… ▽ More

   Submitted 7 December, 2024; v1 submitted 4 November, 2024; originally announced November 2024.

   Comments: 13 pages, 5 figures, Proceedings of the II edition of the Workshop on Unifying Representations in Neural Models (UniReps 2024)

6. arXiv:2410.19781  [pdf, other] 

   eess.SP cs.LG

   Feasibility Analysis of Federated Neural Networks for Explainable Detection of Atrial Fibrillation

   Authors: Diogo Reis Santos, Andrea Protani, Lorenzo Giusti, Albert Sund Aillet, Pierpaolo Brutti, Luigi Serio

   Abstract: Early detection of atrial fibrillation (AFib) is challenging due to its asymptomatic and paroxysmal nature. However, advances in deep learning algorithms and the vast collection of electrocardiogram (ECG) data from devices such as the Internet of Things (IoT) hold great potential for the development of an effective solution. This study assesses the feasibility of training a neural network on a Fed… ▽ More

   Submitted 14 October, 2024; originally announced October 2024.

7. arXiv:2410.13869  [pdf, other] 

   cs.CY cs.DC cs.LG

   A Federated Learning Platform as a Service for Advancing Stroke Management in European Clinical Centers

   Authors: Diogo Reis Santos, Albert Sund Aillet, Antonio Boiano, Usevalad Milasheuski, Lorenzo Giusti, Marco Di Gennaro, Sanaz Kianoush, Luca Barbieri, Monica Nicoli, Michele Carminati, Alessandro E. C. Redondi, Stefano Savazzi, Luigi Serio

   Abstract: The rapid evolution of artificial intelligence (AI) technologies holds transformative potential for the healthcare sector. In critical situations requiring immediate decision-making, healthcare professionals can leverage machine learning (ML) algorithms to prioritize and optimize treatment options, thereby reducing costs and improving patient outcomes. However, the sensitive nature of healthcare d… ▽ More

   Submitted 2 October, 2024; originally announced October 2024.

8. arXiv:2410.07199  [pdf, other] 

   eess.SP cs.LG q-bio.NC

   Towards Explainable Graph Neural Networks for Neurological Evaluation on EEG Signals

   Authors: Andrea Protani, Lorenzo Giusti, Chiara Iacovelli, Albert Sund Aillet, Diogo Reis Santos, Giuseppe Reale, Aurelia Zauli, Marco Moci, Marta Garbuglia, Pierpaolo Brutti, Pietro Caliandro, Luigi Serio

   Abstract: After an acute stroke, accurately estimating stroke severity is crucial for healthcare professionals to effectively manage patient's treatment. Graph theory methods have shown that brain connectivity undergoes frequency-dependent reorganization post-stroke, adapting to new conditions. Traditional methods often rely on handcrafted features that may not capture the complexities of clinical phenomena… ▽ More

   Submitted 24 September, 2024; originally announced October 2024.

   Comments: 7 pages, 7 figures

9. arXiv:2404.11698  [pdf, other] 

   cs.AI cs.DC

   A Secure and Trustworthy Network Architecture for Federated Learning Healthcare Applications

   Authors: Antonio Boiano, Marco Di Gennaro, Luca Barbieri, Michele Carminati, Monica Nicoli, Alessandro Redondi, Stefano Savazzi, Albert Sund Aillet, Diogo Reis Santos, Luigi Serio

   Abstract: Federated Learning (FL) has emerged as a promising approach for privacy-preserving machine learning, particularly in sensitive domains such as healthcare. In this context, the TRUSTroke project aims to leverage FL to assist clinicians in ischemic stroke prediction. This paper provides an overview of the TRUSTroke FL network infrastructure. The proposed architecture adopts a client-server model wit… ▽ More

   Submitted 17 April, 2024; originally announced April 2024.

10. arXiv:2311.14086  [pdf, other] 

    eess.IV cs.CV cs.LG q-bio.NC

    Brain MRI Screening Tool with Federated Learning

    Authors: Roman Stoklasa, Ioannis Stathopoulos, Efstratios Karavasilis, Efstathios Efstathopoulos, Marek Dostál, Miloš Keřkovský, Michal Kozubek, Luigi Serio

    Abstract: In clinical practice, we often see significant delays between MRI scans and the diagnosis made by radiologists, even for severe cases. In some cases, this may be caused by the lack of additional information and clues, so even the severe cases need to wait in the queue for diagnosis. This can be avoided if there is an automatic software tool, which would supplement additional information, alerting… ▽ More

    Submitted 23 November, 2023; originally announced November 2023.

    Comments: 5 pages, 2 figures. Submitted to ISBI 2024 conference

    ACM Class: D.2.2; H.1.2; H.5.2; I.4.8; I.4.6; I.5.1; I.5.4; J.3

11. arXiv:2310.08087  [pdf, other] 

    eess.SP cs.LG

    doi10.1109/CAMAD59638.2023.10478391

    A Carbon Tracking Model for Federated Learning: Impact of Quantization and Sparsification

    Authors: Luca Barbieri, Stefano Savazzi, Sanaz Kianoush, Monica Nicoli, Luigi Serio

    Abstract: Federated Learning (FL) methods adopt efficient communication technologies to distribute machine learning tasks across edge devices, reducing the overhead in terms of data storage and computational complexity compared to centralized solutions. Rather than moving large data volumes from producers (sensors, machines) to energy-hungry data centers, raising environmental concerns due to resource deman… ▽ More

    Submitted 24 May, 2024; v1 submitted 12 October, 2023; originally announced October 2023.

    Comments: accepted for presentation at IEEE CAMAD 2023

    Journal ref: 2023 IEEE 28th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)

10:30 → 11:15 Introduction to SIB

By unlocking the full value of data, the SIB Swiss Institute of Bioinformatics delivers positive impact for society as the national organization for biomedical and biological data in Switzerland.

Introduction to SIB - Marie Dangles - 5 min

Mark Ibberson - 15+5min
Clinical data harmonization and federated analytics

Valérie Barbié - 15+5min
Pathogens surveillance for public health
Diagnostics tools development

11:15 → 11:30 Wrap-up and next steps

11:30 → 12:00 Visit to SynchroCyclotron

The 600-MeV Synchrocyclotron (SC), which came into operation in 1957, was CERN’s first accelerator. It provided beams for CERN’s first experiments in particle and nuclear physics. In 1967, it began supplying beams for a dedicated radioactive-ion-beam facility called ISOLDE, which still carries out research ranging from pure nuclear physics to astrophysics and medical physics. In 1990 the SC closed down after 33 years of service.

Speaker: Alessandro Raimondo (CERN)

12:00 → 13:00 Business Lunch

13:00 → 13:15 Departure from CERN