Probabilistic Matrix Factorization for Automated Machine Learning

TL;DR

This paper presents a probabilistic matrix factorization approach combined with Bayesian optimization to automate the selection and tuning of machine learning pipelines, leading to faster identification of high-performing models across diverse datasets.

Contribution

It introduces a novel meta-learning method that leverages collaborative filtering and Bayesian optimization for automated machine learning pipeline selection.

Findings

Rapidly identifies high-performing pipelines

Outperforms current state-of-the-art methods

Effective across diverse datasets

Abstract

In order to achieve state-of-the-art performance, modern machine learning techniques require careful data pre-processing and hyperparameter tuning. Moreover, given the ever increasing number of machine learning models being developed, model selection is becoming increasingly important. Automating the selection and tuning of machine learning pipelines consisting of data pre-processing methods and machine learning models, has long been one of the goals of the machine learning community. In this paper, we tackle this meta-learning task by combining ideas from collaborative filtering and Bayesian optimization. Using probabilistic matrix factorization techniques and acquisition functions from Bayesian optimization, we exploit experiments performed in hundreds of different datasets to guide the exploration of the space of possible pipelines. In our experiments, we show that our approach quickly identifies high-performing pipelines across a wide range of datasets, significantly outperforming the current state-of-the-art.