The University of Southampton
University of Southampton Institutional Repository

Explanation Shift: Detecting distribution shifts on tabular data via the explanation space

Explanation Shift: Detecting distribution shifts on tabular data via the explanation space
Explanation Shift: Detecting distribution shifts on tabular data via the explanation space
As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In the past, predictive performance was considered the key indicator to monitor. However, explanation aspects have come to attention within the last years. In this work, we investigate how model predictive performance and model explanation characteristics are affected under distribution shifts and how these key indicators are related to each other for tabular data. We find that the modeling of explanation shifts can be a better indicator for the detection of predictive performance changes than state-of-the-art techniques based on representations of distribution shifts. We provide a mathematical analysis of different types of distribution shifts as well as synthetic experimental examples.
Mougan, Carlos
fdfb61c6-eb26-4f8d-87bf-958a2f2234d0
Broelemann, Klaus
591f0927-c503-465e-8b27-e615a564733c
Kasneci, Gjergji
2991f0cd-5693-4843-9da5-af09e489ce7d
Tiropanis, Thanassis
d06654bd-5513-407b-9acd-6f9b9c5009d8
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49
Mougan, Carlos
fdfb61c6-eb26-4f8d-87bf-958a2f2234d0
Broelemann, Klaus
591f0927-c503-465e-8b27-e615a564733c
Kasneci, Gjergji
2991f0cd-5693-4843-9da5-af09e489ce7d
Tiropanis, Thanassis
d06654bd-5513-407b-9acd-6f9b9c5009d8
Staab, Steffen
bf48d51b-bd11-4d58-8e1c-4e6e03b30c49

Mougan, Carlos, Broelemann, Klaus, Kasneci, Gjergji, Tiropanis, Thanassis and Staab, Steffen (2022) Explanation Shift: Detecting distribution shifts on tabular data via the explanation space. NeurIPS 2022 Workshop on Distribution Shifts, , New Orleans, United States. 03 Dec 2022. 9 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

As input data distributions evolve, the predictive performance of machine learning models tends to deteriorate. In the past, predictive performance was considered the key indicator to monitor. However, explanation aspects have come to attention within the last years. In this work, we investigate how model predictive performance and model explanation characteristics are affected under distribution shifts and how these key indicators are related to each other for tabular data. We find that the modeling of explanation shifts can be a better indicator for the detection of predictive performance changes than state-of-the-art techniques based on representations of distribution shifts. We provide a mathematical analysis of different types of distribution shifts as well as synthetic experimental examples.

This record has no associated files available for download.

More information

Published date: 21 November 2022
Venue - Dates: NeurIPS 2022 Workshop on Distribution Shifts, , New Orleans, United States, 2022-12-03 - 2022-12-03

Identifiers

Local EPrints ID: 472849
URI: http://eprints.soton.ac.uk/id/eprint/472849
PURE UUID: c85d44cf-9ee6-495e-a17c-e1b0b8a9c6b7
ORCID for Thanassis Tiropanis: ORCID iD orcid.org/0000-0002-6195-2852
ORCID for Steffen Staab: ORCID iD orcid.org/0000-0002-0780-4154

Catalogue record

Date deposited: 20 Dec 2022 17:36
Last modified: 17 Mar 2024 03:38

Export record

Contributors

Author: Carlos Mougan
Author: Klaus Broelemann
Author: Gjergji Kasneci
Author: Thanassis Tiropanis ORCID iD
Author: Steffen Staab ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×