Recurrent Latent Variable Networks for Session-Based Recommendation

By Sotirios P. Chatzis, Panayiotis Christodoulou, Andreas S. Andreou. 2017

43 citations recorded by the source corpus.

In this work, we attempt to ameliorate the impact of data sparsity in the context of session-based recommendation. Specifically, we seek to devise a machine learning mechanism capable of extracting subtle and complex underlying temporal dynamics in the observed session data, so as to inform the recommendation algorithm. To this end, we improve upon systems that utilize deep learning techniques with recurrently connected units; we do so by adopting concepts from the field of Bayesian statistics, namely variational inference. Our proposed approach consists in treating the network recurrent units as stochastic latent variables with a prior distribution imposed over them. On this basis, we proceed to infer corresponding posteriors; these can be used for prediction and recommendation generation, in a way that accounts for the uncertainty in the available sparse training data. To allow for our approach to easily scale to large real-world datasets, we perform inference under an approximate amortized variational inference (AVI) setup, whereby the learned posteriors are parameterized via (conventional) neural networks. We perform an extensive experimental evaluation of our approach using challenging benchmark datasets, and illustrate its superiority over existing state-of-the-art techniques.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research, Recommender Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

In Management Science and Operations Research

In Recommender Systems

Citations in the corpus

Variational Autoencoders for Collaborative Filtering (2018, methodology): “it choice model [30]. It is also used in the cross-entropy loss2 for multi-class classification. For example, it has been used in recurrent neural networks for session-based sequential recommendation [8, 15, 16, 42, 45] and in feedward neural networks applied to Youtube recommendation [9]. The multi”
Recurrent Neural Networks with Top-k Gains for Session-based Recommendations (2017, neutral): “A recent paper [4] proposes the Bayesian version of GRU4Rec and reports ∼ 0 .”
A Survey on Session-based Recommender Systems (2019, background): “Basic deep neural networ-ks RNN Long and rigidly ordered sessions Model long-term and high-order sequential dependencies The rigid order assumption is too strong for session data [6],[11],[38], [39],[78],[85], [88],[99],[139]”
A review on deep learning for recommender systems: challenges and remedies (2018, methodology): “Moreover, Chatzis et al. (2017) propose an inferential framework over session-based recommender systems based on RNN to alleviate the sparsity issues.”
A Simple Convolutional Generative Network for Next Item Recommendation (2018, background): “While effective, these RNN-based models, such as [3, 15], depend on a hidden state of the entire past that cannot fully utilize parallel computation within a sequence [8].”