Document is current

Article History

Received: 9 July 2024

Revised: 22 July 2025

Accepted: 24 July 2025

First Online: 28 August 2025

Declarations

:

: The authors declare that they have no conflict of interest.

: The main effect of our work is to speed up the learning process and automatically balance classes. Speedup reduces energy consumption and potentially allows for using less powerful hardware for training, a tiny step towards democratizing AI. Balancing classes may help to emphasize underrepresented samples and thus may raise visibility of minorities in data. It depends on the target application if this results in highly desired fair treatment of minorities or an unfair deviation from underlying distributions.

: All presented results are reproducible using our code, which is available as an anonymous repository at .