Preprint

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

M. Jadid Melika Rezaye Garkani A. Mousavi

Aug 2026 · 0 citations · 23 references

Computer Science

TL;DR

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.

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.

arXiv Semantic Scholar

View source

Similar papers

Preprint Jul 2026

TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data

The proposed TabLoRA is a parameter-efficient trainable neural ensemble for large-scale tabular learning that improves the feasibility of neural ensemble learning while preserving much of the benefit of full ensembles.

Jiaqi Luo, Shixin Xu · 0 citations

#machine learning Preprint Aug 2026

TabNSM: Neural Sparse Mixer for Tabular Regression

TabNSM provides an effective and scalable approach to deep tabular regression, and demonstrates that selective interaction modeling, structured regression supervision, and difficulty-aware sampling provide an effective and scalable approach to deep tabular regression.

Ali Eslamian, Qiang Cheng · 0 citations

Preprint Aug 2026

Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN

Localized TabICLv2 introduces a method that reduces the inference cost of TabICLv2 by retrieving only the k nearest training neighbours for each test point, measured by similarity in the model's Stage 2 row-representation space, rather than using the full training context.

Beimnet Bekele Guta · 0 citations

Jul 2026

TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning

This work introduces TabPack, an efficient MLP ensemble with strong out-of-the-box performance and reduced reliance on traditional tuning, and specifies ranges from which to sample MLP hyperparameter rather than exact hyperparameter values, which naturally demands less precision for good performance.

Yury Gorishniy, Akim Kotelnikov, Ivan Rubachev et al. · arXiv.org · 0 citations

Preprint Aug 2026

TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction

This work adopts an alternate approach, sticking with row-based attention while incorporating long context pre-training to eliminate the need for retrieval in TabDPT-Turbo, a model that provides comparable default performance to TabDPT v1.1 on TabArena-Lite, CC18, and CTR23, at orders of magnitude faster.

Rasa Hosseinzadeh, Alex Labach, Zexin Xue et al. · 4 citations

Preprint Jul 2026

Complexity-Budgeted, Interaction-Aware Interpretable Model for Tabular Data

Results support IAIML as a compact, interaction-aware framework appropriate for settings where bounded explanation size and controlled treatment of feature interactions are design requirements.

S. Krishnamoorthy · 0 citations