spark-fm (homepage)

A parallel implementation of factorization machines based on Spark

@chen-lin / (1)

Factorization Machines is a general predictor like SVMs but is also able to estimate reliable parameters under very high sparsity. However, they are costly to scale to large amounts of data and large numbers of features. spark-fm is a parallel implementation of factorization machines based on Spark. It aims to utilize Spark's in-memory computing capability to address above problems.

Highlight
spark-fm supports various optimization methods to satisfy users' requirements.
1. mini-batch stochastic gradient descent ("gd")
2. parallel stochastic gradient descent ("pgd")
3. l-bfgs ("l-bfgs")

Tags

  • 1|machine learning
  • 1|factorization machines

How to

This package doesn't have any releases published in the Spark Packages repo, or with maven coordinates supplied. You may have to build this package from source, or it may simply be a script. To use this Spark Package, please follow the instructions in the README.

Releases

No releases yet.