Salvato in:
Dettagli Bibliografici
Autori principali: Yfantidou, Sofia, Spathis, Dimitris, Constantinides, Marios, Vakali, Athena, Quercia, Daniele, Kawsar, Fahim
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2401.01640
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909060194893824
author Yfantidou, Sofia
Spathis, Dimitris
Constantinides, Marios
Vakali, Athena
Quercia, Daniele
Kawsar, Fahim
author_facet Yfantidou, Sofia
Spathis, Dimitris
Constantinides, Marios
Vakali, Athena
Quercia, Daniele
Kawsar, Fahim
contents Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Hypothesizing that SSL models would learn more generic, hence less biased, representations, this study explores the impact of pre-training and fine-tuning strategies on fairness (i.e., performing equally on different demographic breakdowns). Motivated by human-centric applications on real-world timeseries data, we interpret inductive biases on the model, layer, and metric levels by systematically comparing SSL models to their supervised counterparts. Our findings demonstrate that SSL has the capacity to achieve performance on par with supervised methods while significantly enhancing fairness--exhibiting up to a 27% increase in fairness with a mere 1% loss in performance through self-supervision. Ultimately, this work underscores SSL's potential in human-centric computing, particularly high-stakes, data-scarce application domains like healthcare.
format Preprint
id arxiv_https___arxiv_org_abs_2401_01640
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Fairness in Self-supervised and Supervised Models for Sequential Data
Yfantidou, Sofia
Spathis, Dimitris
Constantinides, Marios
Vakali, Athena
Quercia, Daniele
Kawsar, Fahim
Machine Learning
Computers and Society
Self-supervised learning (SSL) has become the de facto training paradigm of large models where pre-training is followed by supervised fine-tuning using domain-specific data and labels. Hypothesizing that SSL models would learn more generic, hence less biased, representations, this study explores the impact of pre-training and fine-tuning strategies on fairness (i.e., performing equally on different demographic breakdowns). Motivated by human-centric applications on real-world timeseries data, we interpret inductive biases on the model, layer, and metric levels by systematically comparing SSL models to their supervised counterparts. Our findings demonstrate that SSL has the capacity to achieve performance on par with supervised methods while significantly enhancing fairness--exhibiting up to a 27% increase in fairness with a mere 1% loss in performance through self-supervision. Ultimately, this work underscores SSL's potential in human-centric computing, particularly high-stakes, data-scarce application domains like healthcare.
title Evaluating Fairness in Self-supervised and Supervised Models for Sequential Data
topic Machine Learning
Computers and Society
url https://arxiv.org/abs/2401.01640