Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data
Kai Helli, David Schnurr, Noah Hollmann, Samuel Müller, Frank Hutter
–Neural Information Processing Systems
Until now, no tabular method has consistently outperformed classical supervised learning, which ignores these shifts.
Neural Information Processing Systems
Oct-10-2025, 13:47:01 GMT
- Country:
- Asia
- Bangladesh (0.04)
- India > Andhra Pradesh (0.04)
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Singapore (0.04)
- Europe
- France (0.04)
- Germany
- Baden-Württemberg
- Freiburg (0.04)
- Tübingen Region > Tübingen (0.04)
- Bavaria > Upper Bavaria
- Munich (0.04)
- Baden-Württemberg
- Middle East > Republic of Türkiye
- Istanbul Province > Istanbul (0.04)
- Switzerland > Zürich
- Zürich (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- North America > United States
- Iowa > Story County
- Ames (0.04)
- Maryland (0.04)
- Minnesota > Olmsted County (0.04)
- Iowa > Story County
- Oceania > Australia
- New South Wales (0.04)
- South America > Brazil
- Asia
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Banking & Finance (0.92)
- Health & Medicine > Therapeutic Area
- Cardiology/Vascular Diseases (0.93)
- Endocrinology (0.68)
- Transportation (0.92)