Preventing Failures by Dataset Shift Detection in Safety-Critical Graph Applications

Abstract

Dataset shift refers to the problem where the input data distribution may change over time (e.g., between training and test stages). Since this can be a critical bottleneck in several safety-critical applications such as healthcare, drug-discovery, etc., dataset shift detection has become an important research issue in machine learning. Though several existing efforts have focused on image/video data, applications with graph-structured data have not received sufficient attention. Therefore, in this paper, we investigate the problem of detecting shifts in graph structured data through the lens of statistical hypothesis testing. Specifically, we propose a practical two-sample test based approach for shift detection in large-scale graph structured data. Our approach is very flexible in that it is suitable for both undirected and directed graphs, and eliminates the need for equal sample sizes. Using empirical studies, we demonstrate the effectiveness of the proposed test in detecting dataset shifts. We also corroborate these findings using real-world datasets, characterized by directed graphs and a large number of nodes.

Reliable Graph Neural Network Explanations Through Adversarial Training

“…As a result, there is a surge of interest in utilizing these models to make important decisions in high-stakes applications, such as in traffic routing, materials science, and healthcare. [1]- [3]. Despite their success, graph neural networks (GNNs), and more broadly deep neural networks (DNNs), are still critically limited by the their inability to explain their decisions and actions to human users.…”