Article

Automatic Discovery of Intra-Class Sub-Structure for Supervised Tabular Classification: Offline Clustering vs. Joint Sub-Center Training

2026-07-30

Abstract excerpt

<title>Abstract</title> <p>Class labels in real-world tabular data are often coarser than the underlying data-generating process. We revisit, with a rigorous empirical study (5 seeds per dataset), the idea of automatically discovering this hidden intra-class sub-structure to improve supervised tabular classification. First, we show that the conventional two-stage approach - cluster penultimate features per class...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: fac8c449-b22d-57ca-ad41-4ffffc9bd41c
DOI: 10.21203/rs.3.rs-10326626/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Automatic Discovery of Intra-Class Sub-Structure for Supervised Tabular Classification: Offline Clustering vs. Joint Sub-Center TrainingDOI 10.21203/rs.3.rs-10326626/v1Read

S-IGTD: supervised tabular-to-image topology learning via between-group correlation for multiclass classification of biological dataSemantic proximity Read

Short Review: Automated Hyperparameter Tuning Methods for High Accuracy Tabular ClassificationSemantic proximity Read

PhasePilot: Auditing and steering phase boundaries in budgeted in-context reasoningSemantic proximity Read

Intrinsic Thematic Separability in Sentence-Transformer Embeddings: A Controlled Geometric Study from Synthetic to Real-World TextSemantic proximity Read

Self-Supervised Learning Principles Challenges and Emerging DirectionsSemantic proximity Read

An Interpretable AutoML Pipeline: Automated Feature Engineering with FeatureTools and SurXSemantic proximity Read

Scaffolded representation learning in deep networksSemantic proximity Read

Structure Complexity Entropy: A Principle for Structural Intelligence in AISemantic proximity Read

Detecting and Learning from Unknown by Extremely Weak Supervision: eXploratory Classifier (xClass)Semantic proximity Read

Blueprinting the Future: Automatic Item Categorization using Hierarchical Zero-Shot and Few-Shot ClassifiersSemantic proximity Read

Class-Adaptive Ensemble-Vote Consistency for Semi-Supervised Text Classification with Imbalanced DataSemantic proximity Read

A Measurement Note on Pre-Wrap and Reader-Visible Context Accounting for a Capped FLAN-T5 QA PipelineSemantic proximity Read