DeepAI AI Chat
Log In Sign Up

Adherence and Constancy in LIME-RS Explanations for Recommendation

09/02/2021
by   Vito Walter Anelli, et al.
Politecnico di Bari
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/30/2018

Explainable Recommendation: A Survey and New Perspectives

Explainable Recommendation refers to the personalized recommendation alg...
07/17/2018

Explanations for Temporal Recommendations

Recommendation systems are an integral part of Artificial Intelligence (...
12/15/2020

Explainable Recommendation Systems by Generalized Additive Models with Manifest and Latent Interactions

In recent years, the field of recommendation systems has attracted incre...
10/20/2021

Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation

Explainable recommendation systems provide explanations for recommendati...
05/31/2021

Bounded logit attention: Learning to explain image classifiers

Explainable artificial intelligence is the attempt to elucidate the work...
06/18/2021

Rational Shapley Values

Explaining the predictions of opaque machine learning algorithms is an i...
06/15/2021

On the Objective Evaluation of Post Hoc Explainers

Many applications of data-driven models demand transparency of decisions...