arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.16154cs.CVcs.LG
收藏

数据高效泛化是否会加剧基础模型中的偏差?

Does Data-Efficient Generalization Exacerbate Bias in Foundation Models?

Universidade Federal de São Paulo(圣保罗联邦大学);Instituto Federal de Goiás(戈亚斯联邦学院);Idiap Research Institute(伊迪亚普研究所)

Dilermando Queiroz, Anderson Carlos, Maíra Fatoretto, Luis Filipe Nakayama, André Anjos, Lilian Berton

AI总结:

本文以RetFound在BRSET上的微调为例,研究基础模型在数据高效泛化下的公平性,发现其可缩小群体间AUC差距,但数据量减少时会加剧偏差。

摘要:

基础模型已成为在多个领域中具有标签效率的稳健模型。在医学影像领域,由于获取标注数据困难,这些模型有助于推动医学诊断的发展。然而,目前尚不清楚在预训练期间使用大量未标注数据(这些数据因敏感属性的存在而产生偏差)是否会影响模型的公平性。本研究考察了基础模型(RetFound)在微调巴西多标签眼科数据集(BRSET)时的偏差情况,该数据集的人群构成与预训练数据集不同。与监督学习相比,模型评估表明,基础模型有潜力缩小跨性别和年龄组的最大AUC与最小AUC评估之间的差距。然而,在数据高效泛化中,当数据量减少时,模型会加剧偏差。这些发现表明,在数据有限的实际场景中部署基础模型时,应考虑出现公平性问题的可能性。

英文摘要:

Foundation models have emerged as robust models with label efficiency in diverse domains. In medical imaging, these models contribute to the advancement of medical diagnoses due to the difficulty in obtaining labeled data. However, it is unclear whether using a large amount of unlabeled data, biased by the presence of sensitive attributes during pre-training, influences the fairness of the model. This research examines the bias in the Foundation model (RetFound) when it is applied to fine-tune the Brazilian Multilabel Ophthalmological Dataset (BRSET), which has a different population than the pre-training dataset. The model evaluation, in comparison with supervised learning, shows that the Foundation Model has the potential to reduce the gap between the maximum AUC and minimum AUC evaluations across gender and age groups. However, in a data-efficient generalization, the model increases the bias when the data amount decreases. These findings suggest that when deploying a Foundation Model in real-life scenarios with limited data, the possibility of fairness issues should be considered.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑