Path-based summary explanations for graph recommenders (extended version)
Danae Pla Karidi, Evaggelia Pitoura
TL;DR
This work tackles explaining graph-based recommendations at a holistic level by summarizing explanation paths for individuals and groups. It introduces two graph-theoretic strategies, Steiner-Tree (ST) and Prize-Collecting Steiner Tree (PCST), to construct concise subgraphs that encapsulate the rationale behind user- and item-level recommendations, as well as group-level explanations. Empirical results on ML1M-DBpedia and LFM1M show ST generally improves comprehensibility, actionability, redundancy, and relevance, while PCST excels in diversity, privacy, and scalability, with PCST particularly advantageous for larger groups. The study demonstrates that path-based explanations can be effectively compressed without sacrificing interpretability, offering practical benefits for users, item providers, and model developers, and suggests avenues for fairness, alternative prize policies, and broader applicability beyond graph-based recommenders.
Abstract
Path-based explanations provide intrinsic insights into graph-based recommendation models. However, most previous work has focused on explaining an individual recommendation of an item to a user. In this paper, we propose summary explanations, i.e., explanations that highlight why a user or a group of users receive a set of item recommendations and why an item, or a group of items, is recommended to a set of users as an effective means to provide insights into the collective behavior of the recommender. We also present a novel method to summarize explanations using efficient graph algorithms, specifically the Steiner Tree and the Prize-Collecting Steiner Tree. Our approach reduces the size and complexity of summary explanations while preserving essential information, making explanations more comprehensible for users and more useful to model developers. Evaluations across multiple metrics demonstrate that our summaries outperform baseline explanation methods in most scenarios, in a variety of quality aspects.