Abstract:While language models have exceptional capabilities at text generation, they lack a natural inductive bias for emitting numbers and thus struggle in tasks involving reasoning over quantities, especially arithmetics. This has particular relevance in scientific datasets where combinations of text and numerical data are abundant. One fundamental limitation is the nature of the CE loss, which assumes a nominal (categorical) scale and thus cannot convey proximity between generated number tokens. As a remedy, we here present two versions of a number token loss. The first is based on an $L_p$ loss between the ground truth token value and the weighted sum of the predicted class probabilities. The second loss minimizes the Wasserstein-1 distance between the distribution of the predicted output probabilities and the ground truth distribution. These regression-like losses can easily be added to any language model and extend the CE objective during training. We compare the proposed schemes on a mathematics dataset against existing tokenization, encoding, and decoding schemes for improving number representation in language models. Our results reveal a significant improvement in numerical accuracy when equipping a standard T5 model with the proposed loss schemes.
Abstract:As the prevalence of data-driven technologies in healthcare continues to rise, concerns regarding data privacy and security become increasingly paramount. This thesis aims to address the vulnerability of personalized healthcare models, particularly in the context of ECG monitoring, to adversarial attacks that compromise patient privacy. We propose an approach termed "Machine Unlearning" to mitigate the impact of exposed data points on machine learning models, thereby enhancing model robustness against adversarial attacks while preserving individual privacy. Specifically, we investigate the efficacy of Machine Unlearning in the context of personalized ECG monitoring, utilizing a dataset of clinical ECG recordings. Our methodology involves training a deep neural classifier on ECG data and fine-tuning the model for individual patients. We demonstrate the susceptibility of fine-tuned models to adversarial attacks, such as the Fast Gradient Sign Method (FGSM), which can exploit additional data points in personalized models. To address this vulnerability, we propose a Machine Unlearning algorithm that selectively removes sensitive data points from fine-tuned models, effectively enhancing model resilience against adversarial manipulation. Experimental results demonstrate the effectiveness of our approach in mitigating the impact of adversarial attacks while maintaining the pre-trained model accuracy.