@inbook{0581c1c79c3942eabbee464c7bdfe9c9,
title = "An Initial Study of Machine Learning Underspecification Using Feature Attribution Explainable AI Algorithms: A COVID-19 Virus Transmission Case Study",
abstract = "From a dataset, one can construct different machine learning (ML) models with different parameters and/or inductive biases. Although these models give similar prediction performances when tested on data that are currently available, they may not generalise equally well on unseen data. The existence of multiple equally performing models exhibits underspecification of the ML pipeline used for producing such models. In this work, we propose identifying underspecification using feature attribution algorithms developed in Explainable AI. Our hypothesis is: by studying the range of explanations produced by ML models, one can identify underspecification. We validate this by computing explanations using the Shapley additive explainer and then measuring statistical correlations between them. We experiment our approach on multiple datasets drawn from the literature, and in a COVID-19 virus transmission case study.",
author = "James Hinns and Siyuan Liu and Kovvuri, {Veera Raghava Reddy} and Yalcin, {Mehmet Orcun} and Markus Roggenbach",
note = "Funding Information: Acknowledgments. This work is supported by the Welsh Government Office for Science, Ser Cymru III programme – Tackling Covid-19. Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021 ; Conference date: 08-11-2021 Through 12-11-2021",
year = "2021",
month = oct,
day = "25",
doi = "10.1007/978-3-030-89188-6_24",
language = "English",
isbn = "978-3-030-89187-9",
series = "Lecture Notes in Computer Science",
publisher = "Springer, Cham",
pages = "323--335",
editor = "{Ngia Pham}, Duc and Thanaruk Theeramunkong and Guido Governatori and Fenrong Liu",
booktitle = "PRICAI 2021: Trends in Artificial Intelligence",
address = "Switzerland",
}