Does Data-Efficient Generalization Exacerbate Bias in Foundation Models?

• URL: http://arxiv.org/abs/2408.16154v2
• Date: Mon, 2 Sep 2024 16:58:16 GMT
• Title: Does Data-Efficient Generalization Exacerbate Bias in Foundation Models?
• Authors: Dilermando Queiroz, Anderson Carlos, Maíra Fatoretto, Luis Filipe Nakayama, André Anjos, Lilian Berton,
• Abstract summary: Foundation models have emerged as robust models with label efficiency in diverse domains. 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 when it is applied to fine-tune the Brazilian Multilabel Ophthalmological dataset.
• Score: 2.298227866545911
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Intriguing Properties of Data Attribution on Diffusion Models [33.77847454043439]
  Data attribution seeks to trace desired outputs back to training data. Data attribution has become a module to properly assign for high-intuitive or copyrighted data.
  arXiv  Detail & Related papers  (2023-11-01T13:00:46Z)
• Fast Model Debias with Machine Unlearning [54.32026474971696]
  Deep neural networks might behave in a biased manner in many real-world scenarios. Existing debiasing methods suffer from high costs in bias labeling or model re-training. We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
  arXiv  Detail & Related papers  (2023-10-19T08:10:57Z)
• (Predictable) Performance Bias in Unsupervised Anomaly Detection [3.826262429926079]
  Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection. Our study quantified the disparate performance of UAD models against certain demographic subgroups.
  arXiv  Detail & Related papers  (2023-09-25T14:57:43Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• Analyzing Bias in Diffusion-based Face Generation Models [75.80072686374564]
  Diffusion models are increasingly popular in synthetic data generation and image editing applications. We investigate the presence of bias in diffusion-based face generation models with respect to attributes such as gender, race, and age. We examine how dataset size affects the attribute composition and perceptual quality of both diffusion and Generative Adversarial Network (GAN) based face generation models.
  arXiv  Detail & Related papers  (2023-05-10T18:22:31Z)
• Non-Invasive Fairness in Learning through the Lens of Data Drift [88.37640805363317]
  We show how to improve the fairness of Machine Learning models without altering the data or the learning algorithm. We use a simple but key insight: the divergence of trends between different populations, and, consecutively, between a learned model and minority populations, is analogous to data drift. We explore two strategies (model-splitting and reweighing) to resolve this drift, aiming to improve the overall conformance of models to the underlying data.
  arXiv  Detail & Related papers  (2023-03-30T17:30:42Z)
• On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study [65.17429512679695]
  In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions. Despite ADC's intuitive appeal, it remains unclear when training on adversarial datasets produces more robust models.
  arXiv  Detail & Related papers  (2021-06-02T00:48:33Z)
• The unreasonable effectiveness of Batch-Norm statistics in addressing catastrophic forgetting across medical institutions [8.244654685687054]
  We investigate trade-off between model refinement and retention of previously learned knowledge. We propose a simple yet effective approach, adapting Elastic weight consolidation (EWC) using the global batch normalization statistics of the original dataset.
  arXiv  Detail & Related papers  (2020-11-16T16:57:05Z)
• On the Composition and Limitations of Publicly Available COVID-19 X-Ray Imaging Datasets [0.0]
  Data scarcity, mismatch between training and target population, group imbalance, and lack of documentation are important sources of bias. This paper presents an overview of the currently public available COVID-19 chest X-ray datasets.
  arXiv  Detail & Related papers  (2020-08-26T14:16:01Z)
• CHEER: Rich Model Helps Poor Model via Knowledge Infusion [69.23072792708263]
  We develop a knowledge infusion framework named CHEER that can succinctly summarize such rich model into transferable representations. Our empirical results showed that CHEER outperformed baselines by 5.60% to 46.80% in terms of the macro-F1 score on multiple physiological datasets.
  arXiv  Detail & Related papers  (2020-05-21T21:44:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.