Mapping global dynamics of benchmark creation and saturation in artificial intelligence.


Journal

Nature communications
ISSN: 2041-1723
Titre abrégé: Nat Commun
Pays: England
ID NLM: 101528555

Informations de publication

Date de publication:
10 11 2022
Historique:
received: 24 03 2022
accepted: 31 10 2022
entrez: 10 11 2022
pubmed: 11 11 2022
medline: 15 11 2022
Statut: epublish

Résumé

Benchmarks are crucial to measuring and steering progress in artificial intelligence (AI). However, recent studies raised concerns over the state of AI benchmarking, reporting issues such as benchmark overfitting, benchmark saturation and increasing centralization of benchmark dataset creation. To facilitate monitoring of the health of the AI benchmarking ecosystem, we introduce methodologies for creating condensed maps of the global dynamics of benchmark creation and saturation. We curate data for 3765 benchmarks covering the entire domains of computer vision and natural language processing, and show that a large fraction of benchmarks quickly trends towards near-saturation, that many benchmarks fail to find widespread utilization, and that benchmark performance gains for different AI tasks are prone to unforeseen bursts. We analyze attributes associated with benchmark popularity, and conclude that future benchmarks should emphasize versatility, breadth and real-world utility.

Identifiants

pubmed: 36357391
doi: 10.1038/s41467-022-34591-0
pii: 10.1038/s41467-022-34591-0
pmc: PMC9649641
doi:

Types de publication

Journal Article Research Support, Non-U.S. Gov't

Langues

eng

Sous-ensembles de citation

IM

Pagination

6793

Informations de copyright

© 2022. The Author(s).

Références

Bioinformatics. 2005 Jun;21 Suppl 1:i47-56
pubmed: 15961493
Sci Data. 2022 Jun 17;9(1):322
pubmed: 35715466

Auteurs

Simon Ott (S)

Institute of Artificial Intelligence, Medical University of Vienna. Währingerstraße 25a, 1090, Vienna, Austria.

Adriano Barbosa-Silva (A)

Institute of Artificial Intelligence, Medical University of Vienna. Währingerstraße 25a, 1090, Vienna, Austria.
ITTM S.A.-Information Technology for Translational Medicine, Esch-sur-Alzette, 4354, Luxembourg.

Kathrin Blagec (K)

Institute of Artificial Intelligence, Medical University of Vienna. Währingerstraße 25a, 1090, Vienna, Austria.

Jan Brauner (J)

Oxford Applied and Theoretical Machine Learning (OATML) Group, Department of Computer Science, University of Oxford, Oxford, UK.
Future of Humanity Institute, University of Oxford, Oxford, UK.

Matthias Samwald (M)

Institute of Artificial Intelligence, Medical University of Vienna. Währingerstraße 25a, 1090, Vienna, Austria. matthias.samwald@meduniwien.ac.at.

Articles similaires

Humans Artificial Intelligence COVID-19 SARS-CoV-2 Pandemics
Humans Algorithms Software Artificial Intelligence Computer Simulation
Lakes Salinity Archaea Bacteria Microbiota

Classifications MeSH