Variational Autoencoders for Collaborative Filtering

TL;DR

This paper extends variational autoencoders to collaborative filtering with implicit feedback, introducing a multinomial likelihood and Bayesian inference, leading to significant performance improvements over state-of-the-art methods.

Contribution

It proposes a novel VAE-based collaborative filtering model with multinomial likelihood and Bayesian inference, demonstrating superior results and insights into regularization and likelihood choices.

Findings

Outperforms state-of-the-art baselines on real-world datasets

Shows the effectiveness of multinomial likelihood in collaborative filtering

Provides insights into Bayesian inference benefits in recommender systems

Abstract

We extend variational autoencoders (VAEs) to collaborative filtering for implicit feedback. This non-linear probabilistic model enables us to go beyond the limited modeling capacity of linear factor models which still largely dominate collaborative filtering research.We introduce a generative model with multinomial likelihood and use Bayesian inference for parameter estimation. Despite widespread use in language modeling and economics, the multinomial likelihood receives less attention in the recommender systems literature. We introduce a different regularization parameter for the learning objective, which proves to be crucial for achieving competitive performance. Remarkably, there is an efficient way to tune the parameter using annealing. The resulting model and learning algorithm has information-theoretic connections to maximum entropy discrimination and the information bottleneck principle. Empirically, we show that the proposed approach significantly outperforms several state-of-the-art baselines, including two recently-proposed neural network approaches, on several real-world datasets. We also provide extended experiments comparing the multinomial likelihood with other commonly used likelihood functions in the latent factor collaborative filtering literature and show favorable results. Finally, we identify the pros and cons of employing a principled Bayesian inference approach and characterize settings where it provides the most significant improvements.