Adherence and constancy in LIME-RS explanations for recommendation
Author(s)
Anelli, Vito Walter
Bellogín, Alejandro
Di Noia, Tommaso
Paparella, Vincenzo
Date Issued
2021
Type
conferenceObject
Volume
2960
Journal
Abstract
Explainable Recommendation has attracted a lot of attention due to a renewed interest in explainable artificial intelligence. In particular, post-hoc approaches have proved to be the most easily applicable ones to increasingly complex recommendation models, which are then treated as black boxes. The most recent literature has shown that for post-hoc explanations based on local surrogate models, there are problems related to the robustness of the approach itself. This consideration becomes even more relevant in human-related tasks like recommendation. The explanation also has the arduous task of enhancing increasingly relevant aspects of user experience such as transparency or trustworthiness. This paper aims to show how the characteristics of a classical post-hoc model based on surrogates is strongly model-dependent and does not prove to be accountable for the explanations generated.
File(s)![Thumbnail Image]()
Name
LIME-RS.pdf
Description
Published paper
Size
304.23 KB
Format
Adobe PDF
Checksum (MD5)
85332aa29e7264b5b116d1b685ecaeb7
Conference(s)
Joint Workshop of the 3rd Knowledge-Aware and Conversational Recommender Systems and the 5th Recommendation in Complex Environments, KaRS-ComplexRec 2021