Deep Learning feature selection to unhide demographic recommender systems factors

TL;DR

This paper introduces DeepUnHide, a deep learning method that extracts demographic features from hidden factors in recommender systems, enhancing explainability and fairness.

Contribution

It presents a novel gradient-based localization technique for extracting demographic information from matrix factorization models in collaborative filtering.

Findings

DeepUnHide outperforms existing feature selection methods.

The method effectively classifies demographic attributes.

Results demonstrate improved interpretability of recommender systems.

Abstract

Extracting demographic features from hidden factors is an innovative concept that provides multiple and relevant applications. The matrix factorization model generates factors which do not incorporate semantic knowledge. This paper provides a deep learning-based method: DeepUnHide, able to extract demographic information from the users and items factors in collaborative filtering recommender systems. The core of the proposed method is the gradient-based localization used in the image processing literature to highlight the representative areas of each classification class. Validation experiments make use of two public datasets and current baselines. Results show the superiority of DeepUnHide to make feature selection and demographic classification, compared to the state of art of feature selection methods. Relevant and direct applications include recommendations explanation, fairness in collaborative filtering and recommendation to groups of users.