Coupled Variational Recurrent Collaborative Filtering
This work addresses streaming recommendation for users by combining Bayesian learning with deep networks, offering incremental improvements in modeling uncertainties and efficiency.
The authors tackled the problem of streaming recommender systems by proposing a Coupled Variational Recurrent Collaborative Filtering (CVRCF) framework, which integrates probabilistic models and deep neural networks to handle data dynamicity, and it outperformed state-of-the-art methods in temporal dependency modeling and predictive accuracy on three benchmark datasets.
We focus on the problem of streaming recommender system and explore novel collaborative filtering algorithms to handle the data dynamicity and complexity in a streaming manner. Although deep neural networks have demonstrated the effectiveness of recommendation tasks, it is lack of explorations on integrating probabilistic models and deep architectures under streaming recommendation settings. Conjoining the complementary advantages of probabilistic models and deep neural networks could enhance both model effectiveness and the understanding of inference uncertainties. To bridge the gap, in this paper, we propose a Coupled Variational Recurrent Collaborative Filtering (CVRCF) framework based on the idea of Deep Bayesian Learning to handle the streaming recommendation problem. The framework jointly combines stochastic processes and deep factorization models under a Bayesian paradigm to model the generation and evolution of users' preferences and items' popularities. To ensure efficient optimization and streaming update, we further propose a sequential variational inference algorithm based on a cross variational recurrent neural network structure. Experimental results on three benchmark datasets demonstrate that the proposed framework performs favorably against the state-of-the-art methods in terms of both temporal dependency modeling and predictive accuracy. The learned latent variables also provide visualized interpretations for the evolution of temporal dynamics.