An Explainable Autoencoder For Collaborative Filtering Recommendation
This work addresses the need for interpretability in deep learning-based recommender systems for users, but it is incremental as it builds on existing autoencoder methods.
The paper tackles the problem of black-box predictions in autoencoder-based collaborative filtering recommender systems by designing an explainable autoencoder that uses neighborhood-based explanations, though no concrete performance numbers are provided.
Autoencoders are a common building block of Deep Learning architectures, where they are mainly used for representation learning. They have also been successfully used in Collaborative Filtering (CF) recommender systems to predict missing ratings. Unfortunately, like all black box machine learning models, they are unable to explain their outputs. Hence, while predictions from an Autoencoder-based recommender system might be accurate, it might not be clear to the user why a recommendation was generated. In this work, we design an explainable recommendation system using an Autoencoder model whose predictions can be explained using the neighborhood based explanation style. Our preliminary work can be considered to be the first step towards an explainable deep learning architecture based on Autoencoders.