Energy Consumption-Aware Tabular Benchmarks for Neural Architecture Search

Research output: Working paperPreprintResearch

Documents

  • Fulltext

    Final published version, 0.99 MB, PDF document

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.
Original languageEnglish
Publisherarxiv.org
Number of pages13
Publication statusPublished - 12 Oct 2022

Bibliographical note

Source code at https://github.com/PedramBakh/EC-NAS-Bench

    Research areas

  • cs.LG, stat.ML

Number of downloads are based on statistics from Google Scholar and www.ku.dk


No data available

ID: 333626050