Shapley Based Residual Decomposition for Instance Analysis

Tommy Liu; Amanda Barnard

Shapley Based Residual Decomposition for Instance Analysis

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper, we introduce the idea of decomposing the residuals of regression with respect to the data instances instead of features. This allows us to determine the effects of each individual instance on the model and each other, and in doing so makes for a model-agnostic method of identifying instances of interest. In doing so, we can also determine the appropriateness of the model and data in the wider context of a given study. The paper focuses on the possible applications that such a framework brings to the relatively unexplored field of instance analysis in the context of Explainable AI tasks.

Original language	English
Pages (from-to)	21915-21936
Number of pages	22
Journal	Proceedings of Machine Learning Research
Volume	202
Publication status	Published - 2023
Event	40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States Duration: 23 Jul 2023 → 29 Jul 2023

Cite this

@article{772f03ca6db74a1e8d226f7b86b2077e,

title = "Shapley Based Residual Decomposition for Instance Analysis",

abstract = "In this paper, we introduce the idea of decomposing the residuals of regression with respect to the data instances instead of features. This allows us to determine the effects of each individual instance on the model and each other, and in doing so makes for a model-agnostic method of identifying instances of interest. In doing so, we can also determine the appropriateness of the model and data in the wider context of a given study. The paper focuses on the possible applications that such a framework brings to the relatively unexplored field of instance analysis in the context of Explainable AI tasks.",

author = "Tommy Liu and Amanda Barnard",

note = "Publisher Copyright: {\textcopyright} 2023 Proceedings of Machine Learning Research. All rights reserved.; 40th International Conference on Machine Learning, ICML 2023 ; Conference date: 23-07-2023 Through 29-07-2023",

year = "2023",

language = "English",

volume = "202",

pages = "21915--21936",

journal = "Proceedings of Machine Learning Research",

issn = "2640-3498",

publisher = "ML Research Press",

}

TY - JOUR

T1 - Shapley Based Residual Decomposition for Instance Analysis

AU - Liu, Tommy

AU - Barnard, Amanda

PY - 2023

Y1 - 2023

N2 - In this paper, we introduce the idea of decomposing the residuals of regression with respect to the data instances instead of features. This allows us to determine the effects of each individual instance on the model and each other, and in doing so makes for a model-agnostic method of identifying instances of interest. In doing so, we can also determine the appropriateness of the model and data in the wider context of a given study. The paper focuses on the possible applications that such a framework brings to the relatively unexplored field of instance analysis in the context of Explainable AI tasks.

AB - In this paper, we introduce the idea of decomposing the residuals of regression with respect to the data instances instead of features. This allows us to determine the effects of each individual instance on the model and each other, and in doing so makes for a model-agnostic method of identifying instances of interest. In doing so, we can also determine the appropriateness of the model and data in the wider context of a given study. The paper focuses on the possible applications that such a framework brings to the relatively unexplored field of instance analysis in the context of Explainable AI tasks.

UR - http://www.scopus.com/inward/record.url?scp=85174410080&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85174410080

SN - 2640-3498

VL - 202

SP - 21915

EP - 21936

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

T2 - 40th International Conference on Machine Learning, ICML 2023

Y2 - 23 July 2023 through 29 July 2023

ER -

Shapley Based Residual Decomposition for Instance Analysis

Abstract

Other files and links

Fingerprint

Cite this