Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning

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 …

ai models bias biases bias in ai cs.ai cs.lg dataset datasets ensemble fair fine-tuning multiple paper predictions small through train training unbiased