5 accepted papers
To facilitate healthcare delivery, language models (LMs) have significant potential for clinical prediction tasks using electronic health records (EHRs). However, in these high-stakes applications, unreliable decisions can result in significant costs due to compromised patient safety and ethical con…
Influence function, a method from the robust statistics, measures the changes of model parameters or some functions about model parameters with respect to the removal or modification of training instances. It is an efficient and useful post-hoc method for studying the interpretability of machine lea…
Disparate impact has raised serious concerns in machine learning applications and its societal impacts. In response to the need of mitigating discrimination, fairness has been regarded as a crucial property in algorithmic design. In this work, we study the problem of disparate impact on graph-struct…
Deep neural networks (DNNs) can be huge in size, requiring a considerable a mount of energy and computational resources to operate, which limits their applications in numerous scenarios. It is thus of interest to compress DNNs while maintaining their performance levels. We here propose a probabilis…
It has been shown that deep neural network (DNN) based classifiers are vulnerable to human-imperceptive adversarial perturbations which can cause DNN classifiers to output wrong predictions with high confidence. We propose an unsupervised learning approach to detect adversarial inputs without any kn…