Please use this identifier to cite or link to this item:
http://hdl.handle.net/2067/49392
Title: | An Analysis of Local Explanation with LIME-RS | Authors: | Anelli, Vito Walter Bellogín, Alejandro Noia, Tommaso Di Donini, Francesco Maria Paparella, Vincenzo Pomo, Claudio |
Journal: | CEUR WORKSHOP PROCEEDINGS | Issue Date: | 2022 | 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, since they treat as black boxes the increasingly complex recommendation models. 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, from transparency or trustworthiness points of view – like recommendation. We show how the behavior of LIME-RS – a classical post-hoc model based on surrogates – is strongly model-dependent and does not prove to be accountable for the explanations generated. |
URI: | http://hdl.handle.net/2067/49392 | Rights: | Attribution-NonCommercial-NoDerivatives 4.0 International |
Appears in Collections: | D1. Contributo in Atti di convegno |
Files in This Item:
File | Description | Size | Format | Existing users please |
---|---|---|---|---|
IIR-2022-Local-Explanations-LIME-RS.pdf | Printed version | 277.68 kB | Adobe PDF | Request a copy |
Page view(s)
35
Last Week
1
1
Last month
0
0
checked on Apr 20, 2024
Download(s)
1
checked on Apr 20, 2024
Google ScholarTM
Check
This item is licensed under a Creative Commons License