Squeezing Lemons with Hammers: An Evaluation of AutoML and Tabular Deep Learning for Data-Scarce Classification Applications

Ricardo Knauer, Erik Rodner

Keywords: data scarcity, meta-learning, AutoML, deep learning, benchmark

TL;DR: Based on an extensive evaluation of AutoML and deep learning against logistic regression, we recommend to generally try logistic regression for data-scarce applications first and derive best practices for further method selection with tabular data.

Abstract: Many industry verticals are confronted with small-sized tabular data. In this low-data regime, it is currently unclear whether the best performance can be expected from simple baselines, or more complex machine learning approaches that leverage meta-learning and ensembling. On 44 tabular classification datasets with sample sizes $\leq$ 500, we find that L2-regularized logistic regression performs similar to state-of-the-art automated machine learning (AutoML) frameworks (AutoPrognosis, AutoGluon) and off-the-shelf deep neural networks (TabPFN, HyperFast) on the majority of the benchmark datasets. We therefore recommend to consider logistic regression as the first choice for data-scarce applications with tabular data and provide practitioners with best practices for further method selection.

Submission Number: 11