Deep Neural Decision Trees

Code

• github.com/wOOL/DNDT
  OfficialIn papertf★ 0
• github.com/guy-amir/DNDT
  pytorch★ 0
• github.com/JialuJialu/Exist
  none★ 0
• github.com/PierrickPochelu/word_tree_label
  tf★ 0
• github.com/TheBlueSmoke/tf2_dndt
  tf★ 0

Abstract

Deep neural networks have been proven powerful at processing perceptual data, such as images and audio. However for tabular data, tree-based models are more popular. A nice property of tree-based models is their natural interpretability. In this work, we present Deep Neural Decision Trees (DNDT) -- tree models realised by neural networks. A DNDT is intrinsically interpretable, as it is a tree. Yet as it is also a neural network (NN), it can be easily implemented in NN toolkits, and trained with gradient descent rather than greedy splitting. We evaluate DNDT on several tabular datasets, verify its efficacy, and investigate similarities and differences between DNDT and vanilla decision trees. Interestingly, DNDT self-prunes at both split and feature-level.

Reproductions