Energy Consumption-Aware Tabular Benchmarks for Neural Architecture Search
Research output: Working paper › Preprint
Standard
Energy Consumption-Aware Tabular Benchmarks for Neural Architecture Search. / Bakhtiarifard, Pedram; Igel, Christian; Selvan, Raghavendra.
arxiv.org, 2022.Research output: Working paper › Preprint
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - UNPB
T1 - Energy Consumption-Aware Tabular Benchmarks for Neural Architecture Search
AU - Bakhtiarifard, Pedram
AU - Igel, Christian
AU - Selvan, Raghavendra
N1 - Source code at https://github.com/PedramBakh/EC-NAS-Bench
PY - 2022/10/12
Y1 - 2022/10/12
N2 - The demand for large-scale computational resources for Neural Architecture Search (NAS) has been lessened by tabular benchmarks for NAS. Evaluating NAS strategies is now possible on extensive search spaces and at a moderate computational cost. But so far, NAS has mainly focused on maximising performance on some hold-out validation/test set. However, energy consumption is a partially conflicting objective that should not be neglected. We hypothesise that constraining NAS to include the energy consumption of training the models could reveal a sub-space of undiscovered architectures that are more computationally efficient with a smaller carbon footprint. To support the hypothesis, an existing tabular benchmark for NAS is augmented with the energy consumption of each architecture. We then perform multi-objective optimisation that includes energy consumption as an additional objective. We demonstrate the usefulness of multi-objective NAS for uncovering the trade-off between performance and energy consumption as well as for finding more energy-efficient architectures. The updated tabular benchmark, EC-NAS-Bench, is open-sourced to encourage the further exploration of energy consumption-aware NAS.
AB - The demand for large-scale computational resources for Neural Architecture Search (NAS) has been lessened by tabular benchmarks for NAS. Evaluating NAS strategies is now possible on extensive search spaces and at a moderate computational cost. But so far, NAS has mainly focused on maximising performance on some hold-out validation/test set. However, energy consumption is a partially conflicting objective that should not be neglected. We hypothesise that constraining NAS to include the energy consumption of training the models could reveal a sub-space of undiscovered architectures that are more computationally efficient with a smaller carbon footprint. To support the hypothesis, an existing tabular benchmark for NAS is augmented with the energy consumption of each architecture. We then perform multi-objective optimisation that includes energy consumption as an additional objective. We demonstrate the usefulness of multi-objective NAS for uncovering the trade-off between performance and energy consumption as well as for finding more energy-efficient architectures. The updated tabular benchmark, EC-NAS-Bench, is open-sourced to encourage the further exploration of energy consumption-aware NAS.
KW - cs.LG
KW - stat.ML
M3 - Preprint
BT - Energy Consumption-Aware Tabular Benchmarks for Neural Architecture Search
PB - arxiv.org
ER -
ID: 333626050