针对表格分类中类别不平衡问题，改进了先验数据拟合网络的性能。
Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification
- 采用阈值调整策略，利用PFN固有的校准特性提升罕见类识别。
- 下采样方法在保持高精度的同时显著降低推理计算开销。
- 适合处理小样本且类别不均衡的表格数据分类任务。
先验数据拟合网络（PFNs）在表格分类任务中表现卓越。然而，与其他分类器一样，其性能会因类别不平衡而下降，导致稀有类别表现不佳。尽管已有多种缓解类别不平衡影响的技术，但由于PFNs的上下文学习动态特性，基于损失的方法不可行，其他技术也尚未验证。本文适配了几种经典类别不平衡处理方法，并评估其在PFN分类中的表现。结果表明，阈值调整因PFN的校准特性而表现出色；下采样方法则因PFN在小样本下的优异表现而效果相当，且能显著降低推理计算成本。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。