</> Code with Papers by Syntology

Methods › General › Deep Tabular Learning › NODE

Neural Oblivious Decision Ensembles

NODE

42 papers tagged archive 2025-07-28

Introduced by Sergei Popov et al. in Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Neural Oblivious Decision Ensembles (NODE) is a tabular data architecture that consists of differentiable oblivious decision trees (ODT) that are trained end-to-end by backpropagation.

The core building block is a Neural Oblivious Decision Ensemble (NODE) layer. The layer is composed of m differentiable oblivious decision trees (ODTs) of equal depth d. As an input, all m trees get a common vector x ∈ℝⁿ, containing n numeric features. Below we describe a design of a single differentiable ODT.

In its essence, an ODT is a decision table that splits the data along d splitting features and compares each feature to a learned threshold. Then, the tree returns one of the 2ᵈ possible responses, corresponding to the comparisons result. Therefore, each ODT is completely determined by its splitting features f ∈ℝᵈ, splitting thresholds b ∈ℝᵈ and a d-dimensional tensor of responses R ∈ℝ 2 ×2 ×2_d. In this notation, the tree output is defined as:

h(x)=R[1(f₁(x)-b₁), …, 1(f_d(x)-b_d)] where 1(·) denotes the Heaviside function.

PaperSource

Papers archive 2025-07-28

30 shown of 42, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 43 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Time Series5
Image Classification4
image-classification4
Adversarial Robustness2
Autonomous Driving2
Computational Efficiency2
Deep Learning2
Density Estimation2
Model Selection2
Representation Learning2
Self-Supervised Learning2
Spatio-Temporal Forecasting2
Time Series Analysis2
Variational Inference2
BIG-bench Machine Learning1
Collaborative Filtering1
Continuous Control1
Data Augmentation1
Decision Making1
Denoising1

Usage over time archive 2025-07-28

Papers per year tagged with NODE: 2019 to 2025, peak 11 11 0 2019: 1 paper 2019 2020: 0 papers 2020 2021: 6 papers 2021 2022: 11 papers 2022 2023: 10 papers 2023 2024: 8 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (42 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Deep Tabular Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections