CISL Visitor Program: Deep Domain Adaptation for Runtime Prediction in Dynamic Workload Scheduler

CISL Visitor Program:  Deep Domain Adaptation for Runtime Prediction in Dynamic Workload Scheduler / Hoang Nguyen

In High Performance Computing (HPC) systems, users' requested runtime for submitted jobs plays a crucial role in  efficiency. While underestimation of job runtime could terminate jobs before completion, overestimation could result in long queuing of other jobs in HPC systems. In reality, runtime prediction in HPC is challenging due to the complexity and dynamics of running workloads. Most of the current predictive runtime models are trained on static workloads. This poses a risk of over-fitting the predictions with bias from the learned workload distribution. In this work, we propose an adaptation of Correlation Alignment method in our deep neural network architecture (DCORAL) to alleviate the domain shift between workloads for better runtime predictions. Experiments on both Benchmark Dataset and NCAR real-time production Dataset reveal that our proposed method results in a more stable training model across different workloads with low accuracy variance as compared to the other state-of-the-art methods.

Hoang Nguyen is a PhD student in Computer Science at University of Illinois at Chicago. His research interest is Transfer Learning with focus on Few-shot Learning and Zero-shot Learning. He is working on machine learning research in various domains ranging from biological science to natural language processing. Hoang enjoys hiking, rafting, rock climbing or simply spending days in nature.

Date: August 20, 2019

Time: 1:30pm - 2:30pm

Location: ML-132-Main-Seminar-Rm

Building: Mesa Lab

Webcast but will not have live chat:


Room Number: 
132 Main Seminar Room

Type of event:

Will this event be webcast to the public by NCAR|UCAR?: 
Yes - CG1-North Auditorium -
Calendar Timing: 
Tuesday, August 20, 2019 - 1:30pm to 2:30pm

Posted by Gail Rutledge at ext. 1267,

Quick Facts

NCAR is managed by the nonprofit University Corporation for Atmospheric Research on behalf of NSF and the UCAR university community.

  • NCAR is not a federal agency and its employees are not part of the federal personnel system.
  • Our activities complement those of the federal agencies and we work closely with them.

More about us