Energy Efficiency Considerations for Popular AI Benchmarks
This work addresses the need for resource-aware AI development by providing empirical insights into energy efficiency trade-offs for researchers and practitioners, though it is incremental as it fills an information gap without introducing new methods.
The paper tackled the lack of comprehensive energy efficiency data for popular AI benchmarks by conducting 100 experiments, revealing that different datasets have unique efficiency landscapes and methods vary in their likelihood of being efficient.
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.