# Balanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data

> Source: <https://www.machinebrief.com/news/balanced-adaptive-prototype-selection-for-scalable-tabpfn-in-6ysw>
> Published: 2026-08-14 04:00:00+00:00

arXiv:2608.12989v1 Announce Type: new
Abstract: Pretrained tabular foundation models have demonstrated strong predictive capability; however, their application to large-scale datasets remains constrained by the limited inference context. This paper introduces Balanced Adaptive Prototype Selection (BAPS), a framework for constructing compact, information-preserving contexts for scalable TabPFN inference. Without modifying or retraining the pretrained model, BAPS jointly preserves representative structure, informative decision boundaries, local density, class balance, and feature-space diversity. Experiments on the million-row HIGGS and SUSY datasets show that 512 prototypes retain strong predictive performance and reliable calibration, corresponding to an approximately 1,953-fold context compression. All experiments were conducted on an Intel Core i7 CPU with 16 GB RAM and no GPU acceleration. These findings establish effective context construction as a practical mechanism for extending pretrained tabular foundation models to million-scale datasets.