Tabular Data: Is Deep Learning All You Need?

ICLR 2026 Conference Submission16910 Authors

Keywords: tabula data, tabular survey, tabular foundation models, neural networks, tree-based methods, hyperparameter optimization

Abstract:

Tabular data represent one of the most prevalent data formats in applied machine learning, largely because they accommodate a broad spectrum of real-world problems.
Existing literature has studied many of the shortcomings of neural architectures on tabular data and has repeatedly confirmed the scalability and robustness of gradient-boosted decision trees across varied datasets. However, recent deep learning models have not been subjected to a comprehensive evaluation under conditions that allow for a fair comparison with existing classical approaches. This situation motivates an investigation into whether recent deep-learning paradigms outperform classical ML methods on tabular data.
Our survey fills this gap by benchmarking seventeen state-of-the-art methods, spanning neural networks, classical ML and AutoML techniques. Our empirical results over 68 diverse datasets from a well-established benchmark indicate a paradigm shift, where Deep Learning methods outperform classical approaches.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 16910