Variational Factorization Machines for Preference Elicitation in Large-Scale Recommender Systems
This work addresses the scalability issue for practitioners in recommender systems, though it is incremental as it builds on existing Bayesian factorization machine methods.
The paper tackles the slow training of Bayesian factorization machines in large-scale recommender systems by proposing a variational formulation that enables efficient optimization with mini-batch stochastic gradient descent, achieving comparable or better prediction accuracy on several datasets.
Factorization machines (FMs) are a powerful tool for regression and classification in the context of sparse observations, that has been successfully applied to collaborative filtering, especially when side information over users or items is available. Bayesian formulations of FMs have been proposed to provide confidence intervals over the predictions made by the model, however they usually involve Markov-chain Monte Carlo methods that require many samples to provide accurate predictions, resulting in slow training in the context of large-scale data. In this paper, we propose a variational formulation of factorization machines that allows us to derive a simple objective that can be easily optimized using standard mini-batch stochastic gradient descent, making it amenable to large-scale data. Our algorithm learns an approximate posterior distribution over the user and item parameters, which leads to confidence intervals over the predictions. We show, using several datasets, that it has comparable or better performance than existing methods in terms of prediction accuracy, and provide some applications in active learning strategies, e.g., preference elicitation techniques.