Graph neural networks for detecting anomalies in scientific workflows

Hongwei Jin, Krishnan Raghavan, George Papadimitriou, Cong Wang, Anirban Mandal, Mariam Kiran, Ewa Deelman, Prasanna Balaprakash

Abstract: Identifying and addressing anomalies in complex, distributed systems can be challenging for reliable execution of scientific workflows. We model these workflows as directed acyclic graphs (DAGs), w...