Energy Efficiency Considerations for Popular AI Benchmarks
Advances in artificial intelligence need to become more resource-aware and sustainable. This requires clear assessment and reporting of energy efficiency trade-offs, like sacrificing fast running time for higher predictive performance. While first methods for investigating efficiency have been proposed, we still lack comprehensive results for popular methods and data sets. In this work, we attempt to fill this information gap by providing empiric insights for popular AI benchmarks, with a total of 100 experiments. Our findings are evidence of how different data sets all have their own efficiency landscape, and show that methods can be more or less likely to act efficiently.
- Published in:
AI for Energy Innovation Workshop at AAAI Conference on Artificial Intelligence - Type:
Inproceedings - Authors:
Fischer, Raphael; Jakobs, Matthias; Morik, Katharina - Year:
2023
Citation information
Fischer, Raphael; Jakobs, Matthias; Morik, Katharina: Energy Efficiency Considerations for Popular AI Benchmarks, AI for Energy Innovation Workshop at AAAI Conference on Artificial Intelligence, 2023, https://arxiv.org/abs/2304.08359, Fischer.etal.2023b,
@Inproceedings{Fischer.etal.2023b,
author={Fischer, Raphael; Jakobs, Matthias; Morik, Katharina},
title={Energy Efficiency Considerations for Popular AI Benchmarks},
booktitle={AI for Energy Innovation Workshop at AAAI Conference on Artificial Intelligence},
url={https://arxiv.org/abs/2304.08359},
year={2023},
abstract={Advances in artificial intelligence need to become more resource-aware and sustainable. This requires clear assessment and reporting of energy efficiency trade-offs, like sacrificing fast running time for higher predictive performance. While first methods for investigating efficiency have been proposed, we still lack comprehensive results for popular methods and data sets. In this work, we...}}