# A Siamese Deep Forest

## TL;DR

The paper introduces a Siamese Deep Forest (SDF), an alternative to Siamese neural networks, which uses a modified training set and a weighted class distribution to improve similarity measurement, especially with limited data.

## Contribution

It proposes a novel SDF model based on gcForest, incorporating a quadratic optimization for weighting class probabilities to enhance similarity learning.

## Key findings

- Effective distance metric demonstrated in experiments
- Prevents overfitting with limited training data
- Offers an alternative to neural network-based Siamese models

## Abstract

A Siamese Deep Forest (SDF) is proposed in the paper. It is based on the Deep Forest or gcForest proposed by Zhou and Feng and can be viewed as a gcForest modification. It can be also regarded as an alternative to the well-known Siamese neural networks. The SDF uses a modified training set consisting of concatenated pairs of vectors. Moreover, it defines the class distributions in the deep forest as the weighted sum of the tree class probabilities such that the weights are determined in order to reduce distances between similar pairs and to increase them between dissimilar points. We show that the weights can be obtained by solving a quadratic optimization problem. The SDF aims to prevent overfitting which takes place in neural networks when only limited training data are available. The numerical experiments illustrate the proposed distance metric method.