Making Classical Machine Learning Pipelines Differentiable: A Neural Translation Approach

Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously trained using backpropagation. We argue that the isolated t...

Full description

Saved in:
Bibliographic Details
Main Authors Yu, Gyeong-In, Amizadeh, Saeed, Kim, Sehoon, Pagnoni, Artidoro, Chun, Byung-Gon, Weimer, Markus, Interlandi, Matteo
Format Journal Article
LanguageEnglish
Published 10.06.2019
Subjects
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:Classical Machine Learning (ML) pipelines often comprise of multiple ML models where models, within a pipeline, are trained in isolation. Conversely, when training neural network models, layers composing the neural models are simultaneously trained using backpropagation. We argue that the isolated training scheme of ML pipelines is sub-optimal, since it cannot jointly optimize multiple components. To this end, we propose a framework that translates a pre-trained ML pipeline into a neural network and fine-tunes the ML models within the pipeline jointly using backpropagation. Our experiments show that fine-tuning of the translated pipelines is a promising technique able to increase the final accuracy.
DOI:10.48550/arxiv.1906.03822