Search papers, labs, and topics across Lattice.
This paper introduces Balanced Adaptive Prototype Selection (BAPS), a novel framework designed to enhance the inference capabilities of pretrained tabular foundation models on large-scale datasets by creating compact, information-preserving contexts. BAPS achieves this by maintaining critical aspects such as representative structure, informative decision boundaries, local density, class balance, and feature-space diversity without the need for model retraining. Experimental results on the HIGGS and SUSY datasets demonstrate that BAPS can compress context by approximately 1,953-fold while preserving strong predictive performance and reliable calibration with just 512 prototypes.
Achieving nearly 2,000-fold context compression, BAPS enables pretrained tabular models to handle million-row datasets without retraining.
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.
