Work

Towards Local Post-hoc Recommender Systems Explanations

Year: 2021
Type: conference-paper
Abstract: Post-hoc explanation aims at defining a simple local surrogate model to shed light on a prediction produced by a complex, generally black-box, model. In the general context of classification, it has been shown that local surrogates may not be able to always capture a local explanation, i.e. for a specific instance prediction, but rather traduce more of a general behavior of the black-box. This problem is even more complex in a recommendation scenario where classes and decision boundaries are not explicitly defined and where data are very sparse by nature. We show in this paper that it is possible to tackle these problems with an efficient sampling around the recommendation instance to explain, to finally learn a proper local surrogate model. Our experiments show that our method is as accurate or better than the methods of the literature while retrieving more meaningful explainable features locally.
Source: HAL
Language: English
Open Access status: green
OpenAlex ID: W3157816261
FWCI: 0.288
Cites: 28
Cited by: 7
Related to: 10