Intelligent Systems Group

Green Recommender Systems: Down-Sampling Datasets for Energy-Efficient Algorithm Performance

Abstract As recommender systems become increasingly prevalent, the environmental impact and energy efficiency of training these large-scale models have come under scrutiny. This paper investigates the potential for energy-efficient algorithm performance by optimizing dataset sizes through downsampling techniques. We conducted experiments on the MovieLens 100K, 1M, 10M and Amazon Toys Read more…

By Intelligent Systems Group, ago
e fold and not k fold (Green Recommender Systems)

From Theory to Practice: Implementing and Evaluating e-Fold Cross-Validation

Accepted for publication at the International Conference on Artificial Intelligence and Machine Learning Research (CAIMLR). The PDF is available here. Feel free to also read the original proposal that led to the current publication. Abstract In this paper, we present e-fold cross-validation, an energy-efficient alternative to k-fold, which dynamically adjusts Read more…

By Intelligent Systems Group, ago

From Clicks to Carbon: The Ecological Costs of Recommender Systems (Pre-Print)

Full pre-print as PDF: https://arxiv.org/abs/2408.08203 Abstract As global warming soars, the need to assess the environmental impact of research is becoming increasingly urgent. Despite this, few recommender systems research papers address their environmental impact. In this study, we estimate the ecological impact of recommender systems research by reproducing typical experimental Read more…

By Intelligent Systems Group, ago

Erasmus partnership between the University of Gothenburg and the University of Siegen

We proudly announce that the Department of Electrical Engineering and Computer Science at the University of Siegen and the Department of Applied Information Technology at the University of Gothenburg have signed an Erasmus agreement. The agreement will support exchanges and research visits of Master’s students, researchers (e.g. PhD students), and Read more…

By Intelligent Systems Group, ago

Tobias Vente (ISG) visits Prof. Bart Goethals (ADReM Data Lab) at the University of Antwerp

Tobias spent two weeks with Bart Goethels and his team at the ADReM Data Lab at the University of Antwerp. He worked on novel recommender system algorithms incorporating ensembling techniques during this time. Located within the Department of Mathematics and Computer Science, the Adrem Data Lab comprises four faculty members, Read more…

By Intelligent Systems Group, ago

Our Publication at the ECIR 2024: Revealing the Hidden Impact of Top-N Metrics on Optimization in Recommender Systems

Recently, we were delighted to learn that our paper “Revealing the Hidden Impact of Top-N Metrics on Optimization in Recommender Systems” was accepted for the “Full Paper” track at the ECIR 2024. The paper, co-authored by members of our chair, the Intelligent Systems Group, will be presented by one of Read more…

By Intelligent Systems Group, ago

The ISG Siegen presents four papers at the ACM Conference Series on Recommender Systems 2023 (ACM RecSys 2023)

Our Ph.D. students, Tobias Vente, and Lukas Wegmeth, will attend the ACM RecSys 2023 conference in Singapore to present their latest work on Automated Recommender Systems (AutoRecSys) with four papers: two in the Doctoral Symposium, one in the PERSPECTIVES 2023 Workshop, and one in the Demo track. We already posted Read more…

By Intelligent Systems Group, ago

Tobias Vente and Lukas Wegmeth will present their Ph.D. research goals at the ACM RecSys 2023 Doctoral Symposium in Singapore

The ACM RecSys 2023 Doctoral Symposium Chairs accepted the extended abstracts that Tobias Vente and Lukas Wegmeth submitted. Abstracts will be presented by their authors and discussed with the chairs and other students at the conference. The extended abstract was limited to eight pages, and an unusually high amount of Read more…

By Intelligent Systems Group, ago

Prof. Beel at ‘Schloss Dagstuhl’ seminar 23031 ‘Frontiers of Information Access Experimentation for Research and Education’

Update 2023-05: The report is now available on arXiv.org. Prof. Beel was invited to attend the Dagstuhl seminar about ‘Frontiers of Information Access Experimentation for Research and Education‘. The seminar took place from January 15 to January 20, 2023 in Schloss Dagstuhl, and was organized by Christine Bauer (Utrecht University, Read more…

By Intelligent Systems Group, ago