{"url":"/method/node","slug":"node","name":"NODE","full_name":"Neural Oblivious Decision Ensembles","full_name_withheld":false,"description_markdown":"**Neural Oblivious Decision Ensembles (NODE)** is a tabular data architecture that consists of differentiable\r\noblivious decision trees (ODT) that are trained end-to-end by backpropagation. \r\n\r\nThe 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 $x \\in \\mathbb{R}^{n}$, containing $n$ numeric features. Below we describe a design of a single differentiable ODT.\r\n\r\nIn 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 $2^{d}$ possible responses, corresponding to the comparisons result. Therefore, each ODT is completely determined by its splitting features $f \\in \\mathbb{R}^{d}$, splitting thresholds $b \\in \\mathbb{R}^{d}$ and a $d$-dimensional tensor of responses $R \\in \\mathbb{R} \\underbrace{2 \\times 2 \\times 2}_{d}$. In this notation, the tree output is defined as:\r\n\r\n$$\r\nh(x)=R\\left[\\mathbb{1}\\left(f\\_{1}(x)-b_{1}\\right), \\ldots, \\mathbb{1}\\left(f\\_{d}(x)-b\\_{d}\\right)\\right]\r\n$$\r\nwhere $\\mathbb{1}(\\cdot)$ denotes the Heaviside function.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","paper":"/paper/neural-oblivious-decision-ensembles-for-deep","first_author":"Sergei Popov","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/neural-oblivious-decision-ensembles-for-deep"},"source":{"url":"https://arxiv.org/abs/1909.06312v2","title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Deep Tabular Learning","url":"/methods/category/deep-tabular-learning","pwc_aliases":[]}],"n_papers_tagged":42,"archive_num_papers":42,"papers_newest_first":[{"paper":null,"title":"Fully data-driven inverse hyperelasticity with hyper-network neural ODE fields","date":"2025-06-09","arxiv_id":"2506.08146","n_code_links":0,"syntology":null},{"paper":null,"title":"Neural network based control of unknown nonlinear systems via contraction analysis","date":"2025-05-22","arxiv_id":"2505.16511","n_code_links":0,"syntology":null},{"paper":null,"title":"A novel Neural-ODE model for the state of health estimation of lithium-ion battery using charging curve","date":"2025-05-09","arxiv_id":"2505.05803","n_code_links":0,"syntology":null},{"paper":null,"title":"Quantitative Flow Approximation Properties of Narrow Neural ODEs","date":"2025-03-06","arxiv_id":"2503.04068","n_code_links":0,"syntology":null},{"paper":null,"title":"Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches","date":"2025-03-01","arxiv_id":"2503.00575","n_code_links":0,"syntology":null},{"paper":null,"title":"Modeling Neural Networks with Privacy Using Neural Stochastic Differential Equations","date":"2025-01-12","arxiv_id":"2501.06686","n_code_links":0,"syntology":null},{"paper":null,"title":"TRENDy: Temporal Regression of Effective Nonlinear Dynamics","date":"2024-12-04","arxiv_id":"2412.03496","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-quantum-emitter-characterization","title":"Accelerating Quantum Emitter Characterization with Latent Neural Ordinary Differential Equations","date":"2024-11-17","arxiv_id":"2411.11191","n_code_links":1,"syntology":null},{"paper":null,"title":"Identification of Power Systems with Droop-Controlled Units Using Neural Ordinary Differential Equations","date":"2024-11-13","arxiv_id":"2411.08678","n_code_links":0,"syntology":null},{"paper":"/paper/optimising-neural-fractional-differential","title":"Optimising Neural Fractional Differential Equations for Performance and Efficiency","date":"2024-10-20","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"title":"Lyapunov Neural ODE State-Feedback Control Policies","date":"2024-08-31","arxiv_id":"2409.00393","n_code_links":0,"syntology":null},{"paper":null,"title":"Divide And Conquer: Learning Chaotic Dynamical Systems With Multistep Penalty Neural Ordinary Differential Equations","date":"2024-06-30","arxiv_id":"2407.00568","n_code_links":0,"syntology":null},{"paper":null,"title":"Forecasting with an N-dimensional Langevin Equation and a Neural-Ordinary Differential Equation","date":"2024-05-12","arxiv_id":"2405.07359","n_code_links":0,"syntology":null},{"paper":null,"title":"LaTiM: Longitudinal representation learning in continuous-time models to predict disease progression","date":"2024-04-10","arxiv_id":"2404.07091","n_code_links":0,"syntology":null},{"paper":null,"title":"Semi-Supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach","date":"2023-10-19","arxiv_id":"2310.13110","n_code_links":0,"syntology":null},{"paper":null,"title":"LMT: Longitudinal Mixing Training, a Framework to Predict Disease Progression from a Single Image","date":"2023-10-16","arxiv_id":"2310.10420","n_code_links":0,"syntology":null},{"paper":null,"title":"Longitudinal Self-supervised Learning Using Neural Ordinary Differential Equation","date":"2023-10-16","arxiv_id":"2310.10431","n_code_links":0,"syntology":null},{"paper":null,"title":"ASV Station Keeping under Wind Disturbances using Neural Network Simulation Error Minimization Model Predictive Control","date":"2023-10-11","arxiv_id":"2310.07892","n_code_links":0,"syntology":null},{"paper":null,"title":"Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fields","date":"2023-09-11","arxiv_id":"2310.03745","n_code_links":0,"syntology":null},{"paper":null,"title":"Learning low-dimensional dynamics from whole-brain data improves task capture","date":"2023-05-18","arxiv_id":"2305.14369","n_code_links":0,"syntology":null},{"paper":"/paper/node-imgnet-a-pde-informed-effective-and","title":"NODE-ImgNet: a PDE-informed effective and robust model for image denoising","date":"2023-05-18","arxiv_id":"2305.11049","n_code_links":1,"syntology":null},{"paper":null,"title":"Using neural ordinary differential equations to predict complex ecological dynamics from population density data","date":"2023-04-29","arxiv_id":"2305.00338","n_code_links":0,"syntology":null},{"paper":"/paper/ltc-se-expanding-the-potential-of-liquid-time","title":"LTC-SE: Expanding the Potential of Liquid Time-Constant Neural Networks for Scalable AI and Embedded Systems","date":"2023-04-18","arxiv_id":"2304.08691","n_code_links":1,"syntology":null},{"paper":"/paper/modulated-neural-odes-1","title":"Modulated Neural ODEs","date":"2023-02-26","arxiv_id":"2302.13262","n_code_links":1,"syntology":null},{"paper":null,"title":"Learning Subgrid-scale Models with Neural Ordinary Differential Equations","date":"2022-12-20","arxiv_id":"2212.09967","n_code_links":0,"syntology":null},{"paper":"/paper/expressive-architectures-enhance","title":"Expressive architectures enhance interpretability of dynamics-based neural population models","date":"2022-12-07","arxiv_id":"2212.03771","n_code_links":1,"syntology":{"ran":0,"of":8,"unverified":8,"pointer_only":0}},{"paper":"/paper/gread-graph-neural-reaction-diffusion","title":"GREAD: Graph Neural Reaction-Diffusion Networks","date":"2022-11-25","arxiv_id":"2211.14208","n_code_links":1,"syntology":{"ran":3,"of":10,"unverified":7,"pointer_only":3}},{"paper":null,"title":"Physically Consistent Neural ODEs for Learning Multi-Physics Systems","date":"2022-11-11","arxiv_id":"2211.06130","n_code_links":0,"syntology":null},{"paper":"/paper/fi-ode-certified-and-robust-forward","title":"FI-ODE: Certifiably Robust Forward Invariance in Neural ODEs","date":"2022-10-30","arxiv_id":"2210.16940","n_code_links":1,"syntology":null},{"paper":null,"title":"Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems","date":"2022-09-22","arxiv_id":"2209.10740","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/time-series-1","name":"Time Series","papers":5},{"task":"/task/image-classification","name":"Image Classification","papers":4},{"task":"/task/image-classification","name":"image-classification","papers":4},{"task":"/task/adversarial-robustness","name":"Adversarial Robustness","papers":2},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":2},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":2},{"task":"/task/deep-learning","name":"Deep Learning","papers":2},{"task":"/task/density-estimation","name":"Density Estimation","papers":2},{"task":"/task/model-selection","name":"Model Selection","papers":2},{"task":"/task/representation-learning","name":"Representation Learning","papers":2},{"task":"/task/self-supervised-learning","name":"Self-Supervised Learning","papers":2},{"task":"/task/spatio-temporal-forecasting","name":"Spatio-Temporal Forecasting","papers":2},{"task":"/task/time-series","name":"Time Series Analysis","papers":2},{"task":"/task/variational-inference","name":"Variational Inference","papers":2},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/collaborative-filtering","name":"Collaborative Filtering","papers":1},{"task":"/task/continuous-control","name":"Continuous Control","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1}],"tasks_shown":20,"n_tasks":43,"usage_by_year":[{"year":"2019","papers":1},{"year":"2021","papers":6},{"year":"2022","papers":11},{"year":"2023","papers":10},{"year":"2024","papers":8},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/node"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}