Latent Representation Learning for Autoencoder-based Top-K Recommender System

Dongmin Park, Junhyeok Kang, Jae-Gil Lee

http://doi.org/10.5626/JOK.2020.47.2.207

As the number of products on the Internet is growing exponentially, it becomes more difficult for customers to choose the product they want. Many researchers have been actively making efforts to develop appropriate recommender systems that satisfy the potential demand of the customer and increase the profit of the seller. Recently, collaborative filtering methods based on an autoencoder have shown high performance. However, little attention has been paid for improving the recommendation performance by changing the distribution of latent representation. In this paper, we propose the Dense Latent Representation learning method (DenseLR) which is combined with the autoencoder-based collaborative filtering method to further improve product recommendation performance. The key idea of the DenseLR is to tighten collaborative filtering effects on the latent space by effectively densifying the latent representations of user (or item) rating vectors. In performance comparison experiments on three real-world datasets, DenseLR showed the highest recommendation performance for all datasets. Furthermore, DenseLR can be flexibly combined with a wide range of autoencoder-based CF models, and we empirically validated the improvement of the f1@k score ranging from 4.6% to 23.7%.