The recommender systems have long been studied in the literature. The collaborative filtering is one of the widely adopted recommendation techniques which is usually applied on the explicit data, e.g., rating scores. However, the implicit data, e.g., click data, is believed to be able to discover user's latent preferences. Consequently, a number of research attempts have been made towards this issue. In this paper, we propose to adapt the Wasserstein autoencoders for this collaborative filtering task. Particularly, we propose the new loss function by introducing an L 1 regularization term to learn a sparse low-rank representation form for the latent variables. Then, we carefully design (1) the new cost function to minimize the data reconstruction error, and (2) the suitable distance metrics for the calculation of KL divergence between the learned distribution of latent variables and the underlying true data distribution. Rigorous experiments have been evaluated on three widely adopted datasets. Both the state-of-the-art approaches, e.g., Mult-VAE and Mult-DAE, and the baseline models are evaluated and the promising experimental results have demonstrated that the proposed approach is superior to the compared approaches with respect to criteria Recall@R and N DCG@R.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.