5 June 2023
Colloquium by Prof. Dr. Stefan Schulte, Hamburg University of Technology (TUHH)
Today's Machine Learning (ML) approaches are mostly based on a centralized approach, i.e., data is sent to a centralized entity (very often located in the cloud), where ML training is carried out. However, especially in industrial scenarios, companies are very often not keen on sharing their (raw) data with the cloud, especially if ML training and model generation are provided by an external party (e.g., the vendor of a machine).
Federated Learning (FL) offers an alternative approach, by distributing the model generation across different entities. Thus, learning can be conducted close to the data sources, and only the learned model is shared with other entities. This leads to benefits both with regard to data privacy and communication overhead. In this talk, we will motivate FL, provide some insights on how to use it, and discuss some recent research results, e.g., in FL lifecycle management.
Further information about the speaker can be found here:
Date and time: 26.06.2023 17:15, Konrad-Zuse Hörsaal (B-201), Informatics Campus, University of Hamburg
also online via Zoom:
Meeting ID: 937 3517 4299, Passcode: 87303512.