Kolloquium SoSe 2023

Prof. Dr.-Ing. Stefan Schulte

Technische Universität Hamburg
Institute for Data Engineering

Wann: Mo, 26.06.2022, 17:15 Uhr

Wo: Konrad-Zuse-Hörsaal (Raum B-201)

Thema

Federated Learning - Overview and Current Research

Sprache: English

Abstract

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.

Bio

Dr.-Ing. Stefan Schulte is Full Professor at Hamburg University of Technology, head of the Institute for Data Engineering, and leads the Christian Doppler Laboratory Blockchain Technologies for the Internet of Things (CDL-BOT). Before joining TU Hamburg, he was a PhD student at TU Darmstadt (2006-2010), and a Postdoc, Assistant Professor, and Associate Professor at TU Wien (2011-2021).

Findings from his research have been published in more than 100 refereed scholarly publications, including publications in high-tier journals like Information Systems, IEEE Transactions on Services Computing, and IEEE Transactions on Cloud Computing as well as top-tier conferences like the International Conference on Very Large Databases. Prof. Schulte's research strives to provide the means to process (big) data from, within, and beyond the Internet of Things (IoT). An important focus of his research are blockchain technologies, both with regard to the application of blockchains in novel areas (especially the IoT), and fundamental research (especially with regard to blockchain interoperability), as investigated in CDL-BOT.