Green Recommender-Systems at ACM RecSys 2024

There are only a few days left until the 18th ACM Conference on Recommender Systems begins, and one topic is quite prominently represented this year: Green Recommender Systems.

“Green Recommender Systems” are recommender systems designed to minimize their environmental impact throughout their life cycle – from research and design to implementation and operation. Green Recommender Systems typically aim to match the performance of traditional systems but may also accept trade-offs in accuracy or other metrics to prioritize sustainability. Minimizing environmental impact typically but not necessarily means minimizing energy consumption and CO2 emissions. […] Green Recommender Systems’ principles are not tied to specific algorithms or techniques. We also point out that we do not consider recommender systems that recommend eco-friendly items as “green” if the systems themselves are not designed to minimize their environmental impact.

https://recommender-systems.com/news/2024/10/07/green-recommender-systems-a-call-for-attention/

There are at least seven papers this year at the ACM RecSys conference and workshops that address green recommender systems. These papers are as follows (if I missed some, please let me know in the comments). Disclaimer: quite a few papers are from my group.

Full Paper (Repr. Track)

Presented on Wednesday, the 16th of October, during Session 11: Optimisation and Evaluation 1, 17:20 o’clock, Petruzzelli Theater.

From Clicks to Carbon: The Environmental Toll of Recommender Systems. Tobias Vente (University of Siegen), Lukas Wegmeth (University of Siegen), Alan Said (University of Gothenburg) and Joeran Beel (University of Siegen)

Short Paper

Presented during the Tuesday Poster Session on October 15th in the Chamber of Commerce.

Towards Green Recommender Systems: Investigating the Impact of Data Reduction on Carbon Footprint and Algorithm Performances. Giuseppe Spillo (University of Bari Aldo Moro), Allegra De Filippo (DISI Università di Bologna), Cataldo Musto (University of Bari Aldo Moro), Michela Milano (DISI Università di Bologna) and Giovanni Semeraro (University of Bari Aldo Moro).

RecSoGood Workshop

All of the following papers are presented at the RecSoGood Workshop on the 18th of October 2024, in Room C (Polytechnic of Bari).

14 Kg of CO2: Analyzing the Carbon Footprint and Performance of Session-Based Recommendation Algorithms. Alejandro Plaza, Juan Gil and Denis Parra Santander.

RecSys CarbonAtor: Predicting Carbon Footprint of Recommendation System Models. Giuseppe Spillo, Alberto Gaetano Valerio, Felice Franchini, Allegra De Filippo, Cataldo Musto, Michela Milano and Giovanni Semeraro.

Eco-Aware Graph Neural Networks for Sustainable Recommendations. Antonio Purificato and Fabrizio Silvestri.

Green Recommender Systems: Optimizing Dataset Size for Energy-Efficient Algorithm Performance. Ardalan Arabzadeh, Tobias Vente and Joeran Beel. HTML Version.

e-Fold Cross-Validation for Recommender-System Evaluation. Moritz Baumgart, Lukas Wegmeth, Tobias Vente and Joeran Beel

EMERS: Energy Meter for Recommender System. Lukas Wegmeth, Tobias Vente, Alan Said and Joeran Beel