Methods › General › Deep Tabular Learning › NODE
Neural Oblivious Decision Ensembles
NODE
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.
In Syntology about another paper, arXiv:2102.02248: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). About another paper: this answer is about arXiv:2102.02248, while the archive credits arXiv:1909.06312.
Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.
- NODE-GA 2 M · shares_name_tokens (shares name tokens with this name; a different method) · level V3 · retrieve with
get_reference_implementation(name='NODE-GA 2 M')
Origin paper of this answer, arXiv:2102.02248 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 42 · with a code link: 16 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 42 tagged: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 42 of 42, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Fully data-driven inverse hyperelasticity with hyper-network neural ODE fields 9 Jun 2025 · 0 repositories · arXiv:2506.08146
-
Neural network based control of unknown nonlinear systems via contraction analysis 22 May 2025 · 0 repositories · arXiv:2505.16511
-
A novel Neural-ODE model for the state of health estimation of lithium-ion battery using charging curve 9 May 2025 · 0 repositories · arXiv:2505.05803
-
Quantitative Flow Approximation Properties of Narrow Neural ODEs 6 Mar 2025 · 0 repositories · arXiv:2503.04068
-
Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches 1 Mar 2025 · 0 repositories · arXiv:2503.00575
-
Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations 12 Jan 2025 · 0 repositories · arXiv:2501.06686
-
TRENDy: Temporal Regression of Effective Nonlinear Dynamics 4 Dec 2024 · 0 repositories · arXiv:2412.03496
-
Accelerating Quantum Emitter Characterization with Latent Neural Ordinary Differential Equations 17 Nov 2024 · 1 repository · arXiv:2411.11191
-
Identification of Power Systems with Droop-Controlled Units Using Neural Ordinary Differential Equations 13 Nov 2024 · 0 repositories · arXiv:2411.08678
-
Optimising Neural Fractional Differential Equations for Performance and Efficiency 20 Oct 2024 · 2 repositories
-
Lyapunov Neural ODE State-Feedback Control Policies 31 Aug 2024 · 0 repositories · arXiv:2409.00393
-
Divide And Conquer: Learning Chaotic Dynamical Systems With Multistep Penalty Neural Ordinary Differential Equations 30 Jun 2024 · 0 repositories · arXiv:2407.00568
-
Forecasting with an N-dimensional Langevin Equation and a Neural-Ordinary Differential Equation 12 May 2024 · 0 repositories · arXiv:2405.07359
-
LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression 10 Apr 2024 · 0 repositories · arXiv:2404.07091
-
Semi-Supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach 19 Oct 2023 · 0 repositories · arXiv:2310.13110
-
LMT: Longitudinal Mixing Training, a Framework to Predict Disease Progression from a Single Image 16 Oct 2023 · 0 repositories · arXiv:2310.10420
-
Longitudinal Self-supervised Learning Using Neural Ordinary Differential Equation 16 Oct 2023 · 0 repositories · arXiv:2310.10431
-
ASV Station Keeping under Wind Disturbances using Neural Network Simulation Error Minimization Model Predictive Control 11 Oct 2023 · 0 repositories · arXiv:2310.07892
-
Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fields 11 Sep 2023 · 0 repositories · arXiv:2310.03745
-
Learning low-dimensional dynamics from whole-brain data improves task capture 18 May 2023 · 0 repositories · arXiv:2305.14369
-
NODE-ImgNet: a PDE-informed effective and robust model for image denoising 18 May 2023 · 1 repository · arXiv:2305.11049
-
Using neural ordinary differential equations to predict complex ecological dynamics from population density data 29 Apr 2023 · 0 repositories · arXiv:2305.00338
-
LTC-SE: Expanding the Potential of Liquid Time-Constant Neural Networks for Scalable AI and Embedded Systems 18 Apr 2023 · 1 repository · arXiv:2304.08691
-
Modulated Neural ODEs 26 Feb 2023 · 1 repository · arXiv:2302.13262
-
Learning Subgrid-scale Models with Neural Ordinary Differential Equations 20 Dec 2022 · 0 repositories · arXiv:2212.09967
-
Expressive architectures enhance interpretability of dynamics-based neural population models 7 Dec 2022 · 1 repository · arXiv:2212.03771Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
GREAD: Graph Neural Reaction-Diffusion Networks 25 Nov 2022 · 1 repository · arXiv:2211.14208Syntology official (archive's flag): 6 ran · 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 4 pointer-only (licence)
-
Physically Consistent Neural ODEs for Learning Multi-Physics Systems 11 Nov 2022 · 0 repositories · arXiv:2211.06130
-
FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs 30 Oct 2022 · 1 repository · arXiv:2210.16940
-
Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems 22 Sep 2022 · 0 repositories · arXiv:2209.10740
-
Fast fitting of neural ordinary differential equations by Bayesian neural gradient matching to infer ecological interactions from time series data 13 Sep 2022 · 1 repository · arXiv:2209.06184
-
Prediction-based One-shot Dynamic Parking Pricing 30 Aug 2022 · 2 repositories · arXiv:2208.14231
-
Learning via nonlinear conjugate gradients and depth-varying neural ODEs 11 Feb 2022 · 0 repositories · arXiv:2202.05766
-
Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs 14 Jan 2022 · 1 repository · arXiv:2201.05715Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Generative time series models using Neural ODE in Variational Autoencoders 12 Jan 2022 · 1 repository · arXiv:2201.04630
-
Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations 23 Dec 2021 · 0 repositories · arXiv:2112.12707
-
Latent Time Neural Ordinary Differential Equations 23 Dec 2021 · 0 repositories · arXiv:2112.12728
-
Graph Neural Controlled Differential Equations for Traffic Forecasting 7 Dec 2021 · 1 repository · arXiv:2112.03558
-
Characteristic Neural Ordinary Differential Equations 25 Nov 2021 · 0 repositories · arXiv:2111.13207
-
LT-OCF: Learnable-Time ODE-based Collaborative Filtering 8 Aug 2021 · 2 repositories · arXiv:2108.06208Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
PyTorch Tabular: A Framework for Deep Learning with Tabular Data 28 Apr 2021 · 1 repository · arXiv:2104.13638
-
Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data 13 Sep 2019 · 5 repositories · arXiv:1909.06312Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 7 harvested samples)
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.
Usage over time archive 2025-07-28
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
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