From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems
This addresses the need for human-understandable explanations in recommender systems, which is crucial for stakeholders in information filtering applications, though it is incremental as it builds on existing contextualized approaches.
The paper tackles the problem of making deep learning-based recommender systems explainable without sacrificing performance, by proposing three explainable recommendation strategies (whitebox, graybox, blackbox) that use contextual features like item reviews, and shows they achieve competitive ranking performance and generate accurate explanations on five real-world datasets.
With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications. However, many of them remain difficult to diagnose what aspects of the deep models' input drive the final ranking decision, thus, they cannot often be understood by human stakeholders. In this paper, we investigate the dilemma between recommendation and explainability, and show that by utilizing the contextual features (e.g., item reviews from users), we can design a series of explainable recommender systems without sacrificing their performance. In particular, we propose three types of explainable recommendation strategies with gradual change of model transparency: whitebox, graybox, and blackbox. Each strategy explains its ranking decisions via different mechanisms: attention weights, adversarial perturbations, and counterfactual perturbations. We apply these explainable models on five real-world data sets under the contextualized setting where users and items have explicit interactions. The empirical results show that our model achieves highly competitive ranking performance, and generates accurate and effective explanations in terms of numerous quantitative metrics and qualitative visualizations.