2026_IR_15_DEI – Federated Learning Methods for Biomedical Data: Data Quality
Deadline: 16/07/2026
Scientific-Disciplinary Group
09/IINF-05 - Information Processing Systems
Description
The researcher will design and implement federated learning methods for heterogeneous multimodal biomedical data with a specific focus on data quality assessment and quality-aware model training. Within the HEREDITARY project (Horizon Europe RIA, grant 101137074), the activity targets Work Package WP2 (Clinical Use Cases and Federated Networking Infrastructure) and WP3 (Multimodal Semantic Integration Platform). The main tasks include: (i) developing federated data profiling and quality estimation algorithms that operate without centralizing sensitive health data; (ii) designing quality-aware aggregation strategies — such as quality-weighted federated averaging — that account for heterogeneity in data completeness, label accuracy, and distributional shift across clinical sites (non-IID setting)...
Job posting website
Funding body
Dipartimento di Ingegneria dell'Informazione - Università degli studi di Padova
How to apply
View the original posting on the MUR website: Go to MUR website