Related papers: When does Bias Transfer in Transfer Learning?

When does Bias Transfer in Transfer Learning?

URL: http://arxiv.org/abs/2207.02842v1
Date: Wed, 6 Jul 2022 17:58:07 GMT
Title: When does Bias Transfer in Transfer Learning?
Authors: Hadi Salman, Saachi Jain, Andrew Ilyas, Logan Engstrom, Eric Wong, Aleksander Madry
Abstract summary: Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. We demonstrate that there can exist a downside after all: bias transfer, or the tendency for biases of the source model to persist even after adapting the model to the target class.
Score: 89.22641454588278
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias transfer, or the tendency for biases of the source model to persist even after adapting the model to the target class. Through a combination of synthetic and natural experiments, we show that bias transfer both (a) arises in realistic settings (such as when pre-training on ImageNet or other standard datasets) and (b) can occur even when the target dataset is explicitly de-biased. As transfer-learned models are increasingly deployed in the real world, our work highlights the importance of understanding the limitations of pre-trained source models. Code is available at https://github.com/MadryLab/bias-transfer

Related papers

Universality in Transfer Learning for Linear Models [18.427215139020625]
We study the problem of transfer learning in linear models for both regression and binary classification. We provide an exact and rigorous analysis and relate generalization errors (in regression) and classification errors (in binary classification) for the pretrained and fine-tuned models.
arXiv Detail & Related papers (2024-10-03T03:09:09Z)
Model Debiasing by Learnable Data Augmentation [19.625915578646758]
This paper proposes a novel 2-stage learning pipeline featuring a data augmentation strategy able to regularize the training. Experiments on synthetic and realistic biased datasets show state-of-the-art classification accuracy, outperforming competing methods.
arXiv Detail & Related papers (2024-08-09T09:19:59Z)
Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning [63.850451635362425]
Continual learning requires a model to adapt to ongoing changes in the data distribution. We show that the combination of a large language model and an image generation model can similarly provide useful premonitions. We find that the backbone of our pre-trained networks can learn representations useful for the downstream continual learning problem.
arXiv Detail & Related papers (2024-03-12T06:29:54Z)
Ask Your Distribution Shift if Pre-Training is Right for You [74.18516460467019]
In practice, fine-tuning a pre-trained model improves robustness significantly in some cases but not at all in others. We focus on two possible failure modes of models under distribution shift: poor extrapolation and biases in the training data. Our study suggests that, as a rule of thumb, pre-training can help mitigate poor extrapolation but not dataset biases.
arXiv Detail & Related papers (2024-02-29T23:46:28Z)
Variation of Gender Biases in Visual Recognition Models Before and After Finetuning [29.55318393877906]
We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task. We find that supervised models trained on datasets such as ImageNet-21k are more likely to retain their pretraining biases. We also find that models finetuned on larger scale datasets are more likely to introduce new biased associations.
arXiv Detail & Related papers (2023-03-14T03:42:47Z)
A Data-Based Perspective on Transfer Learning [76.30206800557411]
We take a closer look at the role of the source dataset's composition in transfer learning. Our framework gives rise to new capabilities such as pinpointing transfer learning brittleness.
arXiv Detail & Related papers (2022-07-12T17:58:28Z)
How Well Do Sparse Imagenet Models Transfer? [75.98123173154605]
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" datasets. In this work, we perform an in-depth investigation of this phenomenon in the context of convolutional neural networks (CNNs) trained on the ImageNet dataset. We show that sparse models can match or even outperform the transfer performance of dense models, even at high sparsities.
arXiv Detail & Related papers (2021-11-26T11:58:51Z)
Do Adversarially Robust ImageNet Models Transfer Better? [102.09335596483695]
adversarially robust models often perform better than their standard-trained counterparts when used for transfer learning. Our results are consistent with (and in fact, add to) recent hypotheses stating that robustness leads to improved feature representations.
arXiv Detail & Related papers (2020-07-16T17:42:40Z)

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