Graph Based Anomaly Detection in Chimbuko: Feasible or Fallible?
Published in Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC '23), 2023
Download here
A study on the applicability of graph-based deep learning methods for performance anomaly classification in the Chimbuko framework — a performance analytics tool used to monitor and improve the efficiency of large-scale supercomputing applications.
Authors: Chase Phelps, Ankur Lahiry, Tanzima Z Islam, and Christopher Kelly