When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning

• URL: http://arxiv.org/abs/2606.19827v1
• Date: Thu, 18 Jun 2026 06:11:58 GMT
• Title: When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning
• Abstract summary: Self-supervised learning can leverage unlabeled tables in medical research.<n>Recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization.<n>We propose Adaptive Binning, a training-adaptive discretization pretext that couples discretization to learning through a feature-wise coarse-to-fine curriculum.
• Score: 4.300307544233363
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervised learning can leverage these unlabeled tables, and recent binning-based pretexts offer a promising inductive bias, but existing objectives fix a single global quantile discretization and apply feature-agnostic supervision. We propose Adaptive Binning, a training-adaptive discretization pretext for tabular SSL that couples discretization to learning through a feature-wise coarse-to-fine curriculum. Motivated by the spectral bias of neural networks and the principles of curriculum learning, our method progressively refines discretization per feature upon plateau detection and selects representation-aware splits to jointly improve value-space concentration and representation-space coherence. A heterogeneity-aware objective unifies categorical reconstruction with ordinal supervision for numerical features, and experiments on public medical tabular datasets under unified evaluation protocols show consistent gains for linear probing and fine-tuning without dataset-specific discretization tuning. We further introduce a medical tabular SSL benchmark with standardized protocols to support reproducible progress in this underexplored domain. Our code is available at https://github.com/labhai/Adaptive-Binning.

Related papers

• Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training [17.088964553556163]
  We propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of data.<n>First, addressing the inter-feature hierarchy of varying diagnostic importance, we introduce Importance-Aware Adaptive Masking.<n>Second, addressing the intra-feature continuity-discreteness duality, we propose a Soft-Label Discretized Module.<n>Experiments across large-scale dermatology (SLICE-3D, HOP) and ophthalmology (EyePACS) datasets establish a new state-of-the-art (SOTA)
  arXiv  Detail & Related papers  (2026-08-11T05:57:09Z)
• Unifying Active Learning and Semi-Supervised Learning for Medical Image Segmentation [7.337647131220666]
  We propose a unified active semi-supervised framework for medical image segmentation.<n>RegAL evaluates images along three complementary axes, voxel-wise uncertainty, feature diversity, and a novel topological consistency metric.<n>RegAL remains stable with few labeled volumes and consistently outperforms state-of-the-art AL, SSL, and active semi-supervised baselines.
  arXiv  Detail & Related papers  (2026-07-27T19:10:12Z)
• Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world Constraints [6.949977336110437]
  We present a benchmark comparing classical, deep, and TICL models across varying data scale.<n>We propose AWARE, a task-aligned retrieval framework using supervised embedding learning and lightweight adapters.
  arXiv  Detail & Related papers  (2026-04-02T09:56:17Z)
• Dense Feature Learning via Linear Structure Preservation in Medical Data [30.77691570199694]
  Deep learning models for medical data are typically trained using task specific objectives that encourage representations to collapse onto a small number of discriminative directions.<n>We propose dense feature learning, a representation centric framework that explicitly shapes the linear structure of medical embeddings.
  arXiv  Detail & Related papers  (2026-02-07T21:23:35Z)
• AgentScore: Autoformulation of Deployable Clinical Scoring Systems [45.88028371034407]
  We introduce AgentScore, which performs semantically guided optimization in unit-weighted clinical checklists.<n>AgentScore outperforms existing score-generation methods and achieves AUC comparable to more flexible interpretable models.<n>On two additional externally validated tasks, AgentScore achieves higher discrimination than established guideline-based scores.
  arXiv  Detail & Related papers  (2026-01-29T21:11:06Z)
• Contrastive Learning for Semi-Supervised Deep Regression with Generalized Ordinal Rankings from Spectral Seriation [18.192043514568187]
  We extend contrastive regression methods to allow unlabeled data to be used in the semi-supervised setting.<n>Our method can surpass existing state-of-the-art semi-supervised deep regression methods.
  arXiv  Detail & Related papers  (2025-12-10T02:45:23Z)
• Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks [4.993537302467224]
  We propose a method for multi-modal patient-level information extraction using an expert-informed Bayesian network.<n>We propose the use of virtual evidence augmented with a consistency node to provide an interpretable, probabilistic fusion of the models' predictions.<n>We show the potential of our method on the SimSUM dataset.
  arXiv  Detail & Related papers  (2025-11-21T08:59:42Z)
• Probably Approximately Precision and Recall Learning [60.00180898830079]
  A key challenge in machine learning is the prevalence of one-sided feedback.<n>We introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels.<n>We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Boosting Differentiable Causal Discovery via Adaptive Sample Reweighting [62.23057729112182]
  Differentiable score-based causal discovery methods learn a directed acyclic graph from observational data. We propose a model-agnostic framework to boost causal discovery performance by dynamically learning the adaptive weights for the Reweighted Score function, ReScore.
  arXiv  Detail & Related papers  (2023-03-06T14:49:59Z)
• Is margin all you need? An extensive empirical study of active learning on tabular data [66.18464006872345]
  We analyze the performance of a variety of active learning algorithms on 69 real-world datasets from the OpenML-CC18 benchmark. Surprisingly, we find that the classical margin sampling technique matches or outperforms all others, including current state-of-art.
  arXiv  Detail & Related papers  (2022-10-07T21:18:24Z)
• ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning [52.831894583501395]
  Continual learning assumes the incoming data are fully labeled, which might not be applicable in real applications. We propose deep Online Replay with Discriminator Consistency (ORDisCo) to interdependently learn a classifier with a conditional generative adversarial network (GAN) We show ORDisCo achieves significant performance improvement on various semi-supervised learning benchmark datasets for SSCL.
  arXiv  Detail & Related papers  (2021-01-02T09:04:14Z)

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.