Neural Network Conversion of Machine Learning Pipelines
This work addresses the need for unified and optimized inference engines in machine learning, though it is incremental as it extends existing student-teacher methods to non-neural pipelines.
The paper tackles the problem of converting non-neural machine learning pipelines, specifically random forest classifiers, into neural networks via transfer learning, enabling joint optimization and unified inference. Results show that student neural networks can mimic teacher random forests on most of 100 OpenML tasks with proper hyper-parameter selection.
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.