Search for: All records

Differential privacy (DP) is applied when fine-tuning pre-trained language models (LMs) to limit leakage of training examples. While most DP research has focused on improving a model’s privacy-utility tradeoff, some find that DP can be unfair to or biased against underrepresented groups. In this work, we extensively analyze the impact of DP on bias in LMs. We find differentially private training can increase the model bias against protected groups w.r.t AUC-based bias metrics. DP makes it more difficult for the model to differentiate between the positive and negative examples from the protected groups and other groups in the rest of the population. Our results also show that the impact of DP on bias is affected by both the privacy protection level and the underlying distribution of the dataset. 

Deep Learning for Time-series plays a key role in AI for healthcare. To predict the progress of infectious disease outbreaks and demonstrate clear population-level impact, more granular analyses are urgently needed that control for important and potentially confounding county-level socioeconomic and health factors. We forecast US county-level COVID-19 infections using the Temporal Fusion Transformer (TFT). We focus on heterogeneous time-series deep learning model prediction while interpreting the complex spatiotemporal features learned from the data. The significance of the work is grounded in a real-world COVID-19 infection prediction with highly non-stationary, finely granular, and heterogeneous data. 1) Our model can capture the detailed daily changes of temporal and spatial model behaviors and achieves better prediction performance compared to other time-series models. 2) We analyzed the attention patterns from TFT to interpret the temporal and spatial patterns learned by the model. 3) We collected around 2.5 years of socioeconomic and health features for 3142 US counties, such as observed cases, and a number of static (age distribution and health disparity) and dynamic features (vaccination, disease spread, transmissible cases, and social distancing). Using the proposed framework, we have shown that our model can learn complex interactions. Interpreting different impacts at the county level would be crucial for understanding the infection process that can help effective public health decision-making.