Neural Oblivious Decision Ensembles (NODE) is a tabular data architecture that consists of differentiable oblivious decision trees (ODT) that are trained endtoend 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 $x \in \mathbb{R}^{n}$, 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 $2^{d}$ 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:
$$ h(x)=R\left[\mathbb{1}\left(f_{1}(x)b_{1}\right), \ldots, \mathbb{1}\left(f_{d}(x)b_{d}\right)\right] $$ where $\mathbb{1}(\cdot)$ denotes the Heaviside function.
Source: Neural Oblivious Decision Ensembles for Deep Learning on Tabular DataPaper  Code  Results  Date  Stars 

Task  Papers  Share 

Image Classification  4  12.50% 
SelfSupervised Learning  2  6.25% 
Time Series Analysis  2  6.25% 
SpatioTemporal Forecasting  2  6.25% 
Density Estimation  2  6.25% 
Autonomous Driving  2  6.25% 
Model Predictive Control  1  3.13% 
Neural Network simulation  1  3.13% 
Denoising  1  3.13% 
Component  Type 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 