When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data

arXiv:2608.24381 · cs.LG · Submitted 2026-08-25 · Read on arXiv

cs.LG

Submitted: 2026-08-25

Updated: 2026-08-25

Comments: 18 pages, 4 figures, 4 tables

Code: https://github.com/shnd23/ssl-tabular-label-scarcity

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• AUC — 47× in this paper · explained in 2 episodes
• Robustness — 16× in this paper · explained in 5 episodes
• Ablation — 15× in this paper · explained in 1 episode
• Consistency — 14× in this paper · explained in 3 episodes
• Self-Supervised Learning — 8× in this paper · explained in 7 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Self-Supervised Learning (SSL) — 5× in this paper · explained in 4 episodes
• Missing Not At Random — 4× in this paper
• Regularization — 4× in this paper · explained in 3 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Multi-Layer Perceptron — 3× in this paper
• Benchmark — 2× in this paper · explained in 2 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Explainability — 1× in this paper · explained in 3 episodes
• Feature Selection — 1× in this paper · explained in 4 episodes
• Graceful Degradation — 1× in this paper · explained in 2 episodes
• Missing Completely At Random — 1× in this paper
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semi-supervised Learning — 1× in this paper · explained in 4 episodes

Sources

• SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training
• TabTransformer: Tabular Data Modeling Using Contextual Embeddings
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks