Counterfactual reasoning can be effectively employed to perturb user-item interactions, to identify and explain unfairness in GNN-based recommender systems, thus paving the way for more equitable and transparent recommendations. In this study, in collaboration with Francesco Fabbri, Gianni Fenu, Mirko Marras, and Giacomo Medda, and published in the ACM Transactions on Intelligent Systems and Technology, …
Category: Explainability
Counterfactual Graph Augmentation for Consumer Unfairness Mitigation in Recommender Systems
It is possible to effectively address consumer unfairness in recommender systems by using counterfactual explanations to augment the user-item interaction graph. This approach not only leads to fairer outcomes across different demographic groups but also maintains or improves the overall utility of the recommendations. In a study with Francesco Fabbri, Gianni Fenu, Mirko Marras, and …
Reproducibility of Multi-Objective Reinforcement Learning Recommendation: Interplay between Effectiveness and Beyond-Accuracy Perspectives
Controlling various objectives within Multi-Objective Recommender Systems (MORSs). While reinforcing accuracy objectives appears feasible, it is more challenging to individually control diversity and novelty due to their positive correlation. This raises critical questions about the effectiveness of incorporating multiple correlated objectives in MORSs and the potential risks of not having control over them. In a …
Towards Self-Explaining Sequence-Aware Recommendation
The sequence of user-item interactions can be effectively incorporated in the generation of personalized explanations in recommender systems. By modeling user behavior history sequentially, it is possible to enhance the quality and personalization of explanations provided alongside recommendations, without affecting recommendation quality. In a study with Alejandro Ariza-Casabona, Maria Salamó, and Gianni Fenu, published in …
Knowledge is Power, Understanding is Impact: Utility and Beyond Goals, Explanation Quality, and Fairness in Path Reasoning Recommendation
Path reasoning is a notable recommendation approach that models high-order user-product relations, based on a Knowledge Graph (KG). This approach can extract reasoning paths between recommended products and already experienced products and, then, turn such paths into textual explanations for the user. A benchmarking of the state-of-the-art approaches, in terms of accuracy and beyond-accuracy perspectives, …
Reinforcement recommendation reasoning through knowledge graphs for explanation path quality
Knowledge Graph-based recommender systems naturally produce explainable recommendations, by showing the reasoning paths in the knowledge graph (KG) that were followed to select the recommended items. One can define metrics that assess the quality of the explanation paths in terms of recency, popularity, and diversity. Combining in- and post-processing approaches to optimize for both recommendation …
Hands on Explainable Recommender Systems with Knowledge Graphs
This tutorial was presented at the RecSys ’22 conference, with Giacomo Balloccu, Gianni Fenu, and Mirko Marras. On the tutorial’s website, you can find the slides, the video recording of our talk, and the notebooks of the hands-on parts. The goal of this tutorial was to present the RecSys community with recent advances on explainable …
Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations
Being able to assess explanation quality in recommender systems and by shaping recommendation lists that account for explanation quality allows us to produce more effective recommendations. These recommendations can also increase explanation quality according to the proposed properties, fairly across demographic groups. In a SIGIR 2022 paper, with Giacomo Balloccu, Gianni Fenu, and Mirko Marras, …