An alternative for one-hot encoding in neural network models

TL;DR

This paper introduces a binary encoding algorithm for categorical features in neural networks that maintains the property of category-specific weight updates, similar to one-hot encoding, but with a different encoding scheme.

Contribution

It presents a novel binary encoding method with modified forward and backpropagation procedures to ensure category-specific weight updates in neural networks.

Findings

Binary encoding achieves category-specific weight updates

The method preserves the property of one-hot encoding

Potential for more efficient categorical feature representation

Abstract

This paper proposes an algorithm that implements binary encoding of the categorical features of neural network model input data, while also implementing changes in the forward and backpropagation procedures in order to achieve the property of having model weight changes, that result from the neural network learning process for certain data instances of some feature category, only affect the forward pass calculations for input data instances of that same feature category, as it is in the case of utilising one-hot encoding for categorical features.