Deep Variational Autoencoder with Shallow Parallel Path for Top-N Recommendation (VASP)
This work addresses recommendation system accuracy for users by proposing an incremental hybrid method that integrates neural techniques with existing algorithms.
The paper tackles the top-N recommendation problem by combining a deep variational autoencoder (FLVAE) with a neural version of the EASE algorithm (Neural EASE) in a parallel learning framework, achieving state-of-the-art performance on MovieLens 20M and competitive results on the Netflix Prize dataset.
Recently introduced EASE algorithm presents a simple and elegant way, how to solve the top-N recommendation task. In this paper, we introduce Neural EASE to further improve the performance of this algorithm by incorporating techniques for training modern neural networks. Also, there is a growing interest in the recsys community to utilize variational autoencoders (VAE) for this task. We introduce deep autoencoder FLVAE benefiting from multiple non-linear layers without an information bottleneck while not overfitting towards the identity. We show how to learn FLVAE in parallel with Neural EASE and achieve the state of the art performance on the MovieLens 20M dataset and competitive results on the Netflix Prize dataset.