Green Recommender Systems (Green RecSys)

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
8 Recommender Systems Illustration

ISG will present 8 papers and posters at the ACM Recommender Systems Conference and Workshops

We are thrilled that 8 of our 11 submissions to the 18th ACM Recommender-Systems Conference and Workshops (RobustRecSys and RecSoGood) were accepted for publication. Our research was conducted jointly with partners from the University of Gothenburg (Alan Said), the University of Antwerpen (Lien Michiels), and some excellent Bachelor and Master Read more…

By Joeran Beel, 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

e-fold cross-validation: A computing and energy-efficient alternative to k-fold cross-validation with adaptive folds [Proposal]

This proposal is also available as pre-print (PDF) on OSF.io. If you want to cite this proposal, please cite: Introduction K-fold cross-validation is widely regarded as a robust method for model evaluation in machine learning and related fields, including recommender systems. Unlike a simple hold-out split, k-fold cross-validation ensures that Read more…

By Joeran Beel, ago