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

• URL: http://arxiv.org/abs/2608.24381v1
• Date: Tue, 25 Aug 2026 10:39:30 GMT
• Title: When Does Self-Supervised Pretraining Help Tabular Models? A Study of Label Scarcity and Missing Data
• Abstract summary: Self-supervised learning (SSL) has emerged as a promising approach for tabular data.<n>We evaluate a mask-and-recover SSL pretraining objective against training from scratch and classical baselines across 14 classification tasks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised learning (SSL) has emerged as a promising approach for tabular data, yet its efficacy under extreme label scarcity and test-time missingness remains under-explored. In this paper, we evaluate a mask-and-recover SSL pretraining objective against training from scratch and classical baselines across 14 diverse classification tasks. First, while SSL outperforms training from scratch on average and remains competitive with state-of-the-art tree ensembles (achieving ~0.8954 AUC vs. Random Forest's 0.9015 at 10% labels), the SSL-vs-scratch gains exhibit high inter-task variance and lack significance (p = 0.626 at both 5% and 10% labels). Second, contrary to the hypothesis that missing-value imputation objectives universally benefit datasets with native missingness, SSL yields the most reliable improvements on clean datasets, while frequently degrading performance on datasets with high inherent missingness. Third, despite this training variance, SSL-pretrained models achieve a higher average AUC than scratch-trained models under both test-time missingness completely at random (MCAR) injection (+0.0245 AUC, positive on 11 of 14 tasks) and structured missingness shifts (MNAR, +0.0418 AUC, positive on 8 of 14 tasks), though neither difference remains statistically significant after Holm-Bonferroni correction for multiple comparisons (adjusted p = 0.118 and p = 0.518, respectively). Fourth, comparing our mask-and-recover objective against three established tabular SSL baselines (VIME, SCARF, SubTab) under an identical encoder architecture, we find no significant difference from any of them (adjusted p = 0.459, p = 1.000, p = 1.000), indicating our findings reflect general properties of tabular SSL rather than idiosyncrasies of one particular pretext task.

Related papers

• Leakage-Robust Evaluation and Data-Scale Sensitivity of Attention-Enhanced Multi-Task Learning for Joint Fault Diagnosis and Remaining Useful Life Estimation [0.0]
  Multi-task deep learning models can be affected by how sliding-window sequences are split into training and test sets.<n>We show that naive splitting can inflate classification accuracy from a genuine 20-60 percent to 99.9 percent.<n>We introduce a chunk-based, leakage-audited splitting protocol and evaluate all models using five seeds, one-way ANOVA, and Tukey HSD tests.
  arXiv  Detail & Related papers  (2026-07-17T20:33:36Z)
• Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning [6.479513353756828]
  Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery.<n>This study proposes a training strategy and architectural modification to enhance SSL to such corruptions.<n>The method achieves the highest mean linear-probe accuracy among six backbones on EuroSAT, AID, and NWPU-RESISC45.
  arXiv  Detail & Related papers  (2026-04-23T07:07:59Z)
• Self-Training the Neurochaos Learning Algorithm [0.0]
  This study introduces a hybrid semi-supervised learning architecture that integrates Neurochaos Learning (NL) with a threshold-based Self-Training (ST) method to overcome this constraint.<n>The proposed Self-Training Neurochaos Learning (NL+ST) architecture consistently attains superior performance gain relative to standalone ST models.
  arXiv  Detail & Related papers  (2026-01-03T10:24:01Z)
• A Closer Look at Benchmarking Self-Supervised Pre-training with Image Classification [51.35500308126506]
  Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. We study how classification-based evaluation protocols for SSL correlate and how well they predict downstream performance on different dataset types.
  arXiv  Detail & Related papers  (2024-07-16T23:17:36Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Semi-Supervised Learning via Weight-aware Distillation under Class Distribution Mismatch [15.57119122765309]
  We propose a robust SSL framework called Weight-Aware Distillation (WAD) to alleviate the SSL error. WAD captures adaptive weights and high-quality pseudo labels to target instances by exploring point mutual information (PMI) in representation space. We prove that WAD has a tight upper bound of population risk under class distribution mismatch.
  arXiv  Detail & Related papers  (2023-08-23T02:37:34Z)
• PercentMatch: Percentile-based Dynamic Thresholding for Multi-Label Semi-Supervised Classification [64.39761523935613]
  We propose a percentile-based threshold adjusting scheme to dynamically alter the score thresholds of positive and negative pseudo-labels for each class during the training. We achieve strong performance on Pascal VOC2007 and MS-COCO datasets when compared to recent SSL methods.
  arXiv  Detail & Related papers  (2022-08-30T01:27:48Z)
• A semi-supervised Teacher-Student framework for surgical tool detection and localization [2.41710192205034]
  We introduce a semi-supervised learning (SSL) framework in surgical tool detection paradigm. In the proposed work, we train a model with labeled data which initialises the Teacher-Student joint learning. Our results on m2cai16-tool-locations dataset indicate the superiority of our approach on different supervised data settings.
  arXiv  Detail & Related papers  (2022-08-21T17:21:31Z)
• ADT-SSL: Adaptive Dual-Threshold for Semi-Supervised Learning [68.53717108812297]
  Semi-Supervised Learning (SSL) has advanced classification tasks by inputting both labeled and unlabeled data to train a model jointly. This paper proposes an Adaptive Dual-Threshold method for Semi-Supervised Learning (ADT-SSL) Experimental results show that the proposed ADT-SSL achieves state-of-the-art classification accuracy.
  arXiv  Detail & Related papers  (2022-05-21T11:52:08Z)
• Self-supervised Learning is More Robust to Dataset Imbalance [65.84339596595383]
  We investigate self-supervised learning under dataset imbalance. Off-the-shelf self-supervised representations are already more robust to class imbalance than supervised representations. We devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets.
  arXiv  Detail & Related papers  (2021-10-11T06:29:56Z)
• Semi-supervised Contrastive Learning with Similarity Co-calibration [72.38187308270135]
  We propose a novel training strategy, termed as Semi-supervised Contrastive Learning (SsCL) SsCL combines the well-known contrastive loss in self-supervised learning with the cross entropy loss in semi-supervised learning. We show that SsCL produces more discriminative representation and is beneficial to few shot learning.
  arXiv  Detail & Related papers  (2021-05-16T09:13:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.