UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

A Baseline for Shapley Values in MLPs: from Missingness to Neutrality

Izzo, C; Lipani, A; Okhrati, R; Medda, F; (2021) A Baseline for Shapley Values in MLPs: from Missingness to Neutrality. In: ESANN 2021 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learnin. (pp. pp. 605-610). i6doc publication: Online. Green open access

[thumbnail of ES2021-18.pdf]
Preview
Text
ES2021-18.pdf - Published Version

Download (1MB) | Preview

Abstract

Deep neural networks have gained momentum based on their accuracy, but their interpretability is often criticised. As a result, they are labelled as black boxes. In response, several methods have been proposed in the literature to explain their predictions. Among the explanatory methods, Shapley values is a feature attribution method favoured for its robust theoretical foundation. However, the analysis of feature attributions using Shapley values requires choosing a baseline that represents the concept of missingness. An arbitrary choice of baseline could negatively impact the explanatory power of the method and possibly lead to incorrect interpretations. In this paper, we present a method for choosing a baseline according to a neutrality value: as a parameter selected by decision-makers, the point at which their choices are determined by the model predictions being either above or below it. Hence, the proposed baseline is set based on a parameter that depends on the actual use of the model. This procedure stands in contrast to how other baselines are set, i.e. without accounting for how the model is used. We empirically validate our choice of baseline in the context of binary classification tasks, using two datasets: a synthetic dataset and a dataset derived from the financial domain.

Type: Proceedings paper
Title: A Baseline for Shapley Values in MLPs: from Missingness to Neutrality
Event: ESANN 2021: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learnin
ISBN-13: 978287587082-7
Open access status: An open access version is available from UCL Discovery
Publisher version: https://www.esann.org/sites/default/files/proceedi...
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Civil, Environ and Geomatic Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10141778
Downloads since deposit
Loading...
74Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
Loading...

Archive Staff Only

View Item View Item