arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.00910cs.LGcs.AI
收藏

通过集成学习与正则化微调解决偏差问题

Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning

KAUST(阿卜杜拉国王科技大学)

Ahmed Radwan, Layan Zaafarani, Jetana Abudawood, Faisal AlZahrani, Fares Fourati

AI总结:

本文提出一种综合方法,通过数据划分、局部训练、正则化微调与集成学习结合知识蒸馏,在仅有小数据集和有偏差预训练模型的情况下消除AI模型偏差,并在CIFAR10和HAM10000数据集上验证了有效性。

摘要:

解决AI模型中的偏差对于确保公平和准确的预测至关重要。然而,获取用于训练的大型无偏差数据集具有挑战性。本文提出一种综合方法,仅使用小数据集和潜在有偏差的预训练模型,通过多种方法消除AI模型中的偏差。我们通过数据划分、局部训练和正则化微调,利用预训练模型的反偏差训练多个模型,从而获得潜在的反偏差模型。然后,我们对所有模型采用集成学习以实现无偏差预测。为进一步加速集成模型的推理时间,我们最终通过知识蒸馏得出单一的无偏差神经网络。我们在CIFAR10和HAM10000数据集上的实验证明了该方法的有效性,展示了有前景的结果。这项工作有助于在数据可用性有限的情况下,创建更无偏差且可靠的AI模型。

英文摘要:

Addressing biases in AI models is crucial for ensuring fair and accurate predictions. However, obtaining large, unbiased datasets for training can be challenging. This paper proposes a comprehensive approach using multiple methods to remove bias in AI models, with only a small dataset and a potentially biased pretrained model. We train multiple models with the counter-bias of the pre-trained model through data splitting, local training, and regularized fine-tuning, gaining potentially counter-biased models. Then, we employ ensemble learning for all models to reach unbiased predictions. To further accelerate the inference time of our ensemble model, we conclude our solution with knowledge distillation that results in a single unbiased neural network. We demonstrate the effectiveness of our approach through experiments on the CIFAR10 and HAM10000 datasets, showcasing promising results. This work contributes to the ongoing effort to create more unbiased and reliable AI models, even with limited data availability.

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。

↑