A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jung, Yeonsung, Song, Jaeyun, Yang, June Yong, Kim, Jin-Hwa, Kim, Sung-Yub, Yang, Eunho
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915001573310464
author Jung, Yeonsung
Song, Jaeyun
Yang, June Yong
Kim, Jin-Hwa
Kim, Sung-Yub
Yang, Eunho
author_facet Jung, Yeonsung
Song, Jaeyun
Yang, June Yong
Kim, Jin-Hwa
Kim, Sung-Yub
Yang, Eunho
contents Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations without prior knowledge of bias or an unbiased set. However, spurious correlation remains an ongoing challenge, primarily due to the difficulty in precisely detecting these samples. In this paper, inspired by the similarities between mislabeled samples and bias-conflicting samples, we approach this challenge from a novel perspective of mislabeled sample detection. Specifically, we delve into Influence Function, one of the standard methods for mislabeled sample detection, for identifying bias-conflicting samples and propose a simple yet effective remedy for biased models by leveraging them. Through comprehensive analysis and experiments on diverse datasets, we demonstrate that our new perspective can boost the precision of detection and rectify biased models effectively. Furthermore, our approach is complementary to existing methods, showing performance improvement even when applied to models that have already undergone recent debiasing techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00360
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
Jung, Yeonsung
Song, Jaeyun
Yang, June Yong
Kim, Jin-Hwa
Kim, Sung-Yub
Yang, Eunho
Machine Learning
Computer Vision and Pattern Recognition
Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations without prior knowledge of bias or an unbiased set. However, spurious correlation remains an ongoing challenge, primarily due to the difficulty in precisely detecting these samples. In this paper, inspired by the similarities between mislabeled samples and bias-conflicting samples, we approach this challenge from a novel perspective of mislabeled sample detection. Specifically, we delve into Influence Function, one of the standard methods for mislabeled sample detection, for identifying bias-conflicting samples and propose a simple yet effective remedy for biased models by leveraging them. Through comprehensive analysis and experiments on diverse datasets, we demonstrate that our new perspective can boost the precision of detection and rectify biased models effectively. Furthermore, our approach is complementary to existing methods, showing performance improvement even when applied to models that have already undergone recent debiasing techniques.
title A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.00360