Sustainable transparency in Recommender Systems: Bayesian Ranking of Images for Explainability

TL;DR

This paper introduces BRIE, a Bayesian ranking model for explainable recommender systems that improves transparency, reduces computational costs, and lowers environmental impact while outperforming existing models on multiple datasets.

Contribution

BRIE employs Bayesian Pairwise Ranking to enhance training efficiency and effectiveness in generating personalized visual explanations for recommendations.

Findings

Outperforms state-of-the-art models on six datasets

Reduces model size by up to 64 times

Cuts CO2 emissions by up to 75% during training and inference

Abstract

Recommender Systems have become crucial in the modern world, commonly guiding users towards relevant content or products, and having a large influence over the decisions of users and citizens. However, ensuring transparency and user trust in these systems remains a challenge; personalized explanations have emerged as a solution, offering justifications for recommendations. Among the existing approaches for generating personalized explanations, using existing visual content created by users is a promising option to maximize transparency and user trust. State-of-the-art models that follow this approach, despite leveraging highly optimized architectures, employ surrogate learning tasks that do not efficiently model the objective of ranking images as explanations for a given recommendation; this leads to a suboptimal training process with high computational costs that may not be reduced without affecting model performance. This work presents BRIE, a novel model where we leverage Bayesian Pairwise Ranking to enhance the training process, allowing us to consistently outperform state-of-the-art models in six real-world datasets while reducing its model size by up to 64 times and its CO2 emissions by up to 75% in training and inference.