fastFM: A Library for Factorization Machines

TL;DR

fastFM is a versatile library that makes factorization machines accessible for various tasks like regression, classification, and ranking, aiming to broaden their application and facilitate further research.

Contribution

The paper introduces a comprehensive, easy-to-use library for factorization machines supporting multiple solvers and tasks, enhancing their usability and promoting wider adoption.

Findings

Supports regression, classification, and ranking tasks

Provides multiple solvers for flexibility

Simplifies application of FMs in diverse fields

Abstract

Factorization Machines (FM) are only used in a narrow range of applications and are not part of the standard toolbox of machine learning models. This is a pity, because even though FMs are recognized as being very successful for recommender system type applications they are a general model to deal with sparse and high dimensional features. Our Factorization Machine implementation provides easy access to many solvers and supports regression, classification and ranking tasks. Such an implementation simplifies the use of FM's for a wide field of applications. This implementation has the potential to improve our understanding of the FM model and drive new development.