A popular approach to protein design is to combine a generative model with a discriminative
model for conditional sampling. The generative model samples plausible sequences while …

Abstract The Right to Explanation and the Right to be Forgotten are two important principles
outlined to regulate algorithmic decision making and data usage in real-world applications …

Counterfactual inference aims to answer retrospective" what if" questions and thus belongs
to the most fine-grained type of inference in Pearl's causality ladder. Existing methods for …

Abstract The Right to Explanation is an important regulatory principle that allows individuals
to request actionable explanations for algorithmic decisions. However, several technical …

In the rapidly growing literature on explanation algorithms, it often remains unclear what
precisely these algorithms are for and how they should be used. We argue that this is …

Causal inference on networks faces challenges posed in part by violations of standard
identification assumptions due to dependencies between treatment units. Although graph …

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops
in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it …

Learning causal mechanisms involving networked units of data is a notoriously challenging
task with various applications. Graph Neural Networks (GNNs) have proven to be effective …

A key challenge that threatens the widespread use of neural networks in safety-critical
applications is their vulnerability to adversarial attacks. In this paper, we study the second …

One of the challenges for neural networks in real-life applications is the overconfident errors
these models make when the data is not from the original training distribution. Addressing …