Variational Autoencoders for Collaborative Filtering

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.

arXiv comment10 pages, 3 figures. WWW 2018

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Tutorial on Variational Autoencoders
• Session-based Recommendations with Recurrent Neural Networks
• Deep Variational Information Bottleneck
• Neural Collaborative Filtering
• A Neural Autoregressive Approach to Collaborative Filtering
• Improved Recurrent Neural Networks for Session-based Recommendations
• On the challenges of learning with inference networks on sparse, high-dimensional data
• Recurrent Latent Variable Networks for Session-Based Recommendation

Cited by in corpus (10)

• NSML: Meet the MLaaS platform with a real-world case study
• Collaborative Large Language Model for Recommender Systems
• Avoiding Latent Variable Collapse With Generative Skip Models
• Amortized Variational Inference: A Systematic Review
• VOS: a Method for Variational Oversampling of Imbalanced Data
• A Hybrid Variational Autoencoder for Collaborative Filtering
• Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters
• Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback
• A Missing Information Loss function for implicit feedback datasets
• DVE: Dynamic Variational Embeddings with Applications in Recommender Systems