Pith. sign in

REVIEW 12 cited by

Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data

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 1909.06312 v2 pith:OE6XLKFK submitted 2019-09-13 cs.LG stat.ML

Sergei Popov , Stanislav Morozov , Artem Babenko This is my paper
classification cs.LGstat.ML
keywords learningtabulardatadecisiondeepnodearchitectureensembles
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Nowadays, deep neural networks (DNNs) have become the main instrument for machine learning tasks within a wide range of domains, including vision, NLP, and speech. Meanwhile, in an important case of heterogenous tabular data, the advantage of DNNs over shallow counterparts remains questionable. In particular, there is no sufficient evidence that deep learning machinery allows constructing methods that outperform gradient boosting decision trees (GBDT), which are often the top choice for tabular problems. In this paper, we introduce Neural Oblivious Decision Ensembles (NODE), a new deep learning architecture, designed to work with any tabular data. In a nutshell, the proposed NODE architecture generalizes ensembles of oblivious decision trees, but benefits from both end-to-end gradient-based optimization and the power of multi-layer hierarchical representation learning. With an extensive experimental comparison to the leading GBDT packages on a large number of tabular datasets, we demonstrate the advantage of the proposed NODE architecture, which outperforms the competitors on most of the tasks. We open-source the PyTorch implementation of NODE and believe that it will become a universal framework for machine learning on tabular data.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

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

  1. Basis Transformers for Multi-Task Tabular Regression

    cs.LG 2025-06 conditional novelty 7.0 of 10

    Basis transformers beat fine-tuned LLMs on 34 multi-task tabular regression datasets while using five times fewer parameters and no data preprocessing.

  2. Geometry-Aware Uncertainty Coresets for Robust Visual In-Context Learning in Histopathology

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    GAUC selects histopathology ICL coresets in VLM embedding space by jointly optimizing MMD fidelity, prompt-robust mutual-information regularization, and entropy-based uncertainty, matching baseline accuracy with bette...

  3. An Explainable Gaussian Process Auto-encoder for Tabular Data

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A Gaussian-process autoencoder with a latent-space density estimator generates counterfactual examples for tabular data, with competitive or better scores on several evaluation metrics.

  4. TabFlex: Scaling Tabular Learning to Millions with Linear Attention

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Linear attention lets a TabPFN-style model process millions of tabular samples in seconds with near-identical accuracy on small datasets.

  5. When Shift Happens - Confounding Is to Blame

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Under hidden confounding shifts, predictive information reduces to conditional informativeness minus a residual, a result the authors use to explain ERM's surprising OOD competitiveness and the value of all-covariate models.

  6. Early Diagnosis of Atrial Fibrillation Recurrence: A Large Tabular Model Approach with Structured and Unstructured Clinical Data

    cs.LG 2025-05 conditional novelty 6.0 of 10

    TabPFN outperforms SVM and the CHADS2-VASc, HATCH, and APPLE scores at predicting AF recurrence within two years of onset, using NLP-enriched EHR features, but all models remain weak in absolute terms.

  7. TabLoRA: Parameter-Efficient Low-Rank Ensemble Learning for Large-Scale Tabular Data

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Shared-backbone low-rank ensemble adapters let neural tabular models match much of full-ensemble accuracy on large data without linear parameter growth or frequent OOMs.

  8. 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.

  9. 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.

  10. Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data

    cs.LG 2025-08 conditional novelty 4.0 of 10

    Chunked attention, with no retraining, makes TabPFN v2 handle long tabular contexts exactly and shows accuracy keeps improving past the old 10K limit.

  11. Bridging Electronic Health Records and Clinical Texts: Contrastive Learning for Enhanced Clinical Tasks

    cs.CL 2025-05 conditional novelty 4.0 of 10

    A contrastive pretraining step that aligns static EHR tables with discharge notes improves downstream TabNet predictions on MIMIC-IV readmission and critical outcome tasks.

  12. Random at First, Fast at Last: NTK-Guided Fourier Pre-Processing for Tabular DL

    cs.LG 2025-06 conditional novelty 3.0 of 10

    Fixed random Fourier projections on tabular inputs are claimed to bound the NTK, speed up gradient descent, and improve accuracy across four architectures and eight benchmarks.

Pith tools