Towards Large Scale Training Of Autoencoders For Collaborative Filtering

TL;DR

This paper introduces a mini-batch negative sampling technique to efficiently train autoencoders for large-scale, sparse implicit feedback data in collaborative filtering, achieving comparable performance to state-of-the-art models.

Contribution

It presents a novel mini-batch negative sampling method that enables scalable training of autoencoders for collaborative filtering on large datasets.

Findings

The method achieves similar accuracy to baseline models.

Training is significantly faster on large datasets.

Source code is publicly available.

Abstract

In this paper, we apply a mini-batch based negative sampling method to efficiently train a latent factor autoencoder model on large scale and sparse data for implicit feedback collaborative filtering. We compare our work against a state-of-the-art baseline model on different experimental datasets and show that this method can lead to a good and fast approximation of the baseline model performance. The source code is available in https://github.com/amoussawi/recoder .