Other (O2)

A general-purpose toolbox for efficient Kronecker-based learning




List of Authors: Michiel Stock, Tapio Pahikkala, Antti Airola, Bernard De Baets

Conference name: Juliacon 2020

Publication year: 2020

Book title *: JuliaCon Proceedings

Volume number: 2

Issue number: 13

Number of pages: 2

DOI: http://dx.doi.org/10.21105/jcon.00015

Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/50365239


Abstract

Pairwise learning is a machine learning paradigm where the goal
is to predict properties of pairs of objects. Applications include
recommender systems, molecular network inference, and ecological interaction prediction. Kronecker-based learning systems provide a simple yet elegant method to learn from such pairs. Using
tricks from linear algebra, these models can be trained, tuned, and
validated on large datasets. Our Julia package Kronecker.jl
aggregates these shortcuts and efficient algorithms using a lazily evaluated Kronecker product ‘⊗’, such that it is easy to experiment
with learning algorithms using the Kronecker product.


Downloadable publication

This is an electronic reprint of the original article.
This reprint may differ from the original in pagination and typographic detail. Please cite the original version.




Last updated on 2022-07-04 at 18:42