An Explainable Autoencoder For Collaborative Filtering Recommendation

Authors

Pegah Sagheb Haghighi, University of Louisville
Olurotimi Seton, University of Louisville
Olfa Nasraoui, University of LouisvilleFollow

Document Type

Article

Publication Date

2019

Department

Computer Engineering and Computer Science

Abstract

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 Autoencoderbased 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.

Comments

This is the preprint version of the article, which can be found at: https://arxiv.org/pdf/2001.04344.pdf

ThinkIR Citation

Haghighi, Pegah Sagheb; Seton, Olurotimi; and Nasraoui, Olfa, "An Explainable Autoencoder For Collaborative Filtering Recommendation" (2019). Faculty and Staff Scholarship. 429.
https://ir.library.louisville.edu/faculty/429

ORCID

0000-0003-0999-5385