Generalized test utilities for long-tail performance in extreme multi-label classification
Erik Schultheis, Marek Wydmuch, Wojciech Kotłowski, Rohit Babbar, Krzysztof Dembczyński
–Neural Information Processing Systems
However, it is often argued that correct predictions in the tail are more "interesting" or "rewarding," but the community has not yet settled on a metric capturing this intuitive concept.
Neural Information Processing Systems
Feb-11-2026, 05:57:09 GMT
- Country:
- South America > Brazil
- Rio de Janeiro > Rio de Janeiro (0.04)
- Oceania > Australia
- New South Wales > Sydney (0.04)
- North America
- United States > Georgia
- Fulton County > Atlanta (0.04)
- Canada > Quebec
- Montreal (0.04)
- United States > Georgia
- Europe
- Austria > Vienna (0.14)
- Italy > Sardinia (0.04)
- United Kingdom
- Spain > Andalusia
- Granada Province > Granada (0.04)
- Poland > Greater Poland Province
- Poznań (0.04)
- France
- Hauts-de-France > Nord
- Lille (0.04)
- Auvergne-Rhône-Alpes > Lyon
- Lyon (0.04)
- Hauts-de-France > Nord
- Finland > Uusimaa
- Helsinki (0.04)
- Asia > Middle East
- Jordan (0.04)
- South America > Brazil
- Genre:
- Research Report > New Finding (0.45)
- Technology: