Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

A MULTI-OBJECTIVE APPROACH FOR SUSTAINABLE GENERATIVE AUDIO MODELS

Abstract : In recent years, the deep learning community has largely focused on the accuracy of deep generative models, resulting in impressive improvements in several research fields. However, this scientific race for quality comes at a tremendous computational cost, which incurs vast energy consumption and greenhouse gas emissions. If the current exponential growth of computational consumption persists, Artificial Intelligence (AI) will sadly become a considerable contributor to global warming. At the heart of this problem are the measures that we use as a scientific community to evaluate our work. Currently, researchers in the field of AI judge scientific works mostly based on the improvement in accuracy, log-likelihood, reconstruction or opinion scores, all of which entirely obliterates the actual computational cost of generative models. In this paper, we introduce the idea of relying on a multi-objective measure based on Pareto optimality, which simultaneously integrates the models accuracy, as well as the environmental impact of their training. By applying this measure on the current state-of-the-art in generative audio models, we show that this measure drastically changes the perceived significance of the results in the field, encouraging optimal training techniques and resource allocation. We hope that this type of measure will be widely adopted, in order to help the community to better evaluate the significance of their work, while bringing computational cost-and in fine carbon emissions-in the spotlight of AI research.
Complete list of metadata

https://hal.sorbonne-universite.fr/hal-03296897
Contributor : Jean-Pierre Briot <>
Submitted on : Thursday, July 22, 2021 - 9:48:19 PM
Last modification on : Wednesday, July 28, 2021 - 4:04:09 AM

File

2107.02621.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03296897, version 1
  • ARXIV : 2107.02621

Citation

Constance Douwes, Philippe Esling, Jean-Pierre Briot. A MULTI-OBJECTIVE APPROACH FOR SUSTAINABLE GENERATIVE AUDIO MODELS. 2021. ⟨hal-03296897⟩

Share

Metrics

Record views

12

Files downloads

25