Our paper titled “Energy vs Privacy: Estimating the Ecological Impact of FederatedLearning” has been accepted for publication at the 14th ACM International Conference on Future Energy Systems (e-Energy 2023)!
Our paper titled “The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey” has just been accepted for publication at ACM Computing Systems. In the paper, we draw parallels between distributed graph processing, deep learning and graph neural network systems. It brings together our differentContinue reading “Paper accepted at ACM Computing Surveys!”
Our paper titled “A Survey on Dataset Distillation: Approaches, Applications and Future Directions” has been accepted for publication at the 32nd International Joint Conference on Artificial Intelligence!
I’ve started a new position as a tenured professor of computer science at the University of Bayreuth. I’m going to build up a new research group there, the Chair of Data Systems. If you’re interested in a PhD or PostDoc position, please contact me!
Our paper titled “Partitioner Selection with EASE to Optimize Distributed Graph Processing” has been accepted at IEEE International Conference on Data Engineering (ICDE 2023). It explores the use of machine learning to automate the selection of the optimal graph partitioning algorithm for a given distributed graph processing problem.
I’m happy to announce that our project “CLOUDSTARS – Cloud Open Source Research Mobility Network” has been granted. There are in total 18 partners from industry and academia with a funding volume of 1.4 M EUR. The project allows the partners to send researchers to the corresponding partner institution to perform research together.
Our paper titled “Federated Office Plug-Load Identification for Building Management Systems” has been accepted at the Thirteenth ACM International Conference on Future Energy Systems (ACM e-Energy 2022)!
I am apointed as a mentor of the EXIST-funded startup RYVER.AI. They provide software to generate synthetic data and assess its privacy as well as quality. More information: https://ryver.ai/ Find more information on EXIST: https://www.exist.de/
Our paper titled “Where is My Training Bottleneck? Hidden Trade-Offs in Deep Learning Preprocessing Pipelines” has been accepted for publication at the SIGMOD 2022 conference. In this paper, we provide an in-depth analysis of data preprocessing pipelines from four different machine learning domains. We introduce a new perspective on efficiently preparing datasets for end-to-end deepContinue reading “SIGMOD Paper Accepted!”
I’m happy to announce that we’ve received funding for a new research project at TUM, titled “Federated Learning for Non-Invasive Condition Monitoring”. The funding is sufficient to support one PhD student for three years (see job posting). Many thanks to the Federal Ministry for Economic Affiars and Energy (BMWi) for funding this exciting research!
Our paper titled “MDMS: Music Data Matching System for Query Variant Retrieval” has been accepted in the demos and videos program of the ACM Multimedia 2021 conference. Co-authors were Rinita Roy and Hans-Arno Jacobsen.