Pith. sign in

REVIEW 8 cited by

TabNet: Attentive Interpretable Tabular Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1908.07442 v5 pith:U7ESEVSA submitted 2019-08-20 cs.LG stat.ML

Sercan O. Arik , Tomas Pfister This is my paper
classification cs.LGstat.ML
keywords learningtabnettabulardatainterpretabledecisiondemonstratefeatures
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a novel high-performance and interpretable canonical deep tabular data learning architecture, TabNet. TabNet uses sequential attention to choose which features to reason from at each decision step, enabling interpretability and more efficient learning as the learning capacity is used for the most salient features. We demonstrate that TabNet outperforms other neural network and decision tree variants on a wide range of non-performance-saturated tabular datasets and yields interpretable feature attributions plus insights into the global model behavior. Finally, for the first time to our knowledge, we demonstrate self-supervised learning for tabular data, significantly improving performance with unsupervised representation learning when unlabeled data is abundant.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The Importance of Encoder Choice:A Tabular-Image Study

    cs.LG 2026-07 conditional novelty 6.5 of 10

    Tabular encoder choice reorders multimodal rankings, can erase apparent fusion gains, and requires non-vanilla extraction for in-context learning models to avoid train-test representation shift.

  2. CACTI: Leveraging Copy Masking and Contextual Information to Improve Tabular Data Imputation

    cs.LG 2025-06 conditional novelty 6.0 of 10

    CACTI combines median-truncated copy masking with language-model column embeddings to improve tabular imputation accuracy across MCAR, MAR, and MNAR missingness.

  3. Multimodal Attention-based Deep Learning for Emergency Triage with Electronic Health Records

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Replacing the CNN fusion layer in a TabNet+BERT triage model with a Vision Transformer encoder yields ~2% higher accuracy, F1, and ROC AUC on 11,102 emergency-department records, though the evaluation has unresolved i...

  4. PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models

    cs.AI 2026-04 unverdicted novelty 5.0 of 10

    Spline numerical encodings can match or beat standard scaling on tabular nets, but PLE is most robust for classification and learnable knots add substantial training cost.

  5. Mixing Configurations for Downstream Prediction

    cs.LG 2025-10 conditional novelty 5.0 of 10

    Mixing multiple resolution clusterings of an embedding, aligned between train and test, and fused by attention, improves downstream regression and classification over single-resolution baselines.

  6. Label-Free Concept Drift Assessment for Reliable AI in Emerging Wireless Applications

    cs.NI 2025-07 reject novelty 5.0 of 10

    CFPT and TabAutoDrift detect concept drift by comparing macro-F1 scores from pseudo-label or transfer-learning retraining, reaching F1 of 0.94 in fingerprinting and 1.00 in link anomalies without post-deployment labels.

  7. Calibrated Tree-Neural Fusion for Fine-Grained Vegetation Community Classification

    cs.LG 2026-07 conditional novelty 4.0 of 10

    Calibrated EcoTreeFuseNet-Plus matches ExtraTrees on 29-class vegetation labels while cutting expected calibration error from 0.39 to 0.07 via temperature scaling and leakage-aware stacking.

  8. AI-Driven Vehicle Condition Monitoring with Cell-Aware Edge Service Migration

    cs.NI 2025-06 conditional novelty 4.0 of 10

    A LightGBM-based vehicle fault detector and cell-triggered edge service migration were tested on a real 5G race circuit, giving 15 ms inference but 24 to 67 s migration and weak detection of sparse anomalies.

Pith tools