Platform for Analytics and Distributed Machine Learning for Enterprises
PADME is a Distributed Analytics (DA) infrastructure that brings the algorithms to the data instead of vice versa. By following this paradigm shift, it proposes a solution for persistent privacy-related challenges. It is developed in compliance with Personal Health Train(PHT) approach. It provides a generic solution not limited to the health domain but any domain that need to analyze distributed data.
PHT is a novel approach, aiming to establish a distributed data analytics infrastructure enabling the (re)use of distributed healthcare data, while data owners stay in control of their data. The main principle of the PHT is that data remains in its original location, and analytical tasks visit data sources and execute the tasks. The PHT provides a distributed, flexible approach to use data in a network of participants, incorporating the FAIR principles.
PADME in a nutshell
- Implementation of the PHT/Federated Learning concepts by using FAIR standards
- Result of a collaboration between four research institutes Fraunhofer FIT – Fraunhofer FIT; UNIVERSITÄT ZU KÖLN (uni-koeln.de) DBIS (rwth-aachen.de), Universität Leipzig: www.uni-leipzig.de
- Based on containerization technologies (www.docker.com), deployable on Kubernetes env.
- Benefits:
- Operating system agnostic
- Data source and data structure agnostic
- Programming-language agnostic
Our study is part of German MII and GoFAIR initiatives.
Please see 3min Pitch to know more about PADME
https://padme-analytics.de/, https://docs.padme-analytics.de/