Efficient Mixed Dimension Embeddings for Matrix Factorization
Despite the prominence of neural network approaches in the field of recommender systems, simple methods such as matrix factorization with quadratic loss are still used in industry for several reasons. These models can be trained with alternating least squares, which makes them easy to implement in a...
Gespeichert in:
Hauptverfasser: | , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Despite the prominence of neural network approaches in the field of
recommender systems, simple methods such as matrix factorization with quadratic
loss are still used in industry for several reasons. These models can be
trained with alternating least squares, which makes them easy to implement in a
massively parallel manner, thus making it possible to utilize billions of
events from real-world datasets. Large-scale recommender systems need to
account for severe popularity skew in the distributions of users and items, so
a lot of research is focused on implementing sparse, mixed dimension or shared
embeddings to reduce both the number of parameters and overfitting on rare
users and items. In this paper we propose two matrix factorization models with
mixed dimension embeddings, which can be optimized in a massively parallel
fashion using the alternating least squares approach. |
---|---|
DOI: | 10.48550/arxiv.2205.11248 |