Abstract:Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performance can suffer under the effect of class imbalance, resulting in poor performance for rare classes. Several techniques exist which attempt to mitigate the deleterious effect of class imbalance on classification performance, but the in-context learning (ICL) dynamic of PFNs means that loss-based strategies are impossible, and other techniques are unproven. We have adapted several classical techniques addressing class imbalance and analyzed their performance on PFN classification. We observe that thresholding performs exceptionally well because of the calibration characteristics of PFNs, and downsampling performs comparably because of PFNs exceptional limited-data performance, with the additional benefit of reduced computation cost for inference.
| Comments: | 5 pages, 6 figures, Information Theory Workshop (ITW) |
| Subjects: | Machine Learning (cs.LG); Information Theory (cs.IT) |
| Cite as: | arXiv:2605.21742 [cs.LG] |
| (or arXiv:2605.21742v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.21742 arXiv-issued DOI via DataCite (pending registration) |
From: Samuel McDowell [view email]
[v1]
Wed, 20 May 2026 21:10:54 UTC (365 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。