Neural Network Conversion of Machine Learning Pipelines

TL;DR

This paper explores transferring knowledge from traditional machine learning pipelines, specifically random forests, to neural networks, enabling unified inference and joint optimization across multiple ML tasks.

Contribution

It extends student-teacher learning to non-neural pipelines, demonstrating effective transfer from random forests to neural networks across diverse tasks.

Findings

Student NNs can mimic random forest performance with proper hyper-parameter tuning

Transfer learning from non-neural pipelines is feasible and effective

Random forest-based hyper-parameter selection improves NN transfer results

Abstract

Transfer learning and knowledge distillation has recently gained a lot of attention in the deep learning community. One transfer approach, the student-teacher learning, has been shown to successfully create ``small'' student neural networks that mimic the performance of a much bigger and more complex ``teacher'' networks. In this paper, we investigate an extension to this approach and transfer from a non-neural-based machine learning pipeline as teacher to a neural network (NN) student, which would allow for joint optimization of the various pipeline components and a single unified inference engine for multiple ML tasks. In particular, we explore replacing the random forest classifier by transfer learning to a student NN. We experimented with various NN topologies on 100 OpenML tasks in which random forest has been one of the best solutions. Our results show that for the majority of the tasks, the student NN can indeed mimic the teacher if one can select the right NN hyper-parameters. We also investigated the use of random forest for selecting the right NN hyper-parameters.