Ariful Azad, an assistant professor of intelligent systems engineering at the Luddy School of Informatics, Computing, and Engineering, has been awarded a grant worth $750,000 over five years for research as part of the U.S. Department of Energy’s Early Career Research Program.
Azad’s proposal, “Intelligent Primitives for Scalable Graph Analytics and Learning,” aims to fill the need for high-performance and general-purpose graph analysis and machine learning algorithms to better understand scientific datasets. He will address the challenges of the diversity of scientific data and the heterogeneity of cyberinfrastructure by mapping graph algorithms to a handful of intelligent computational kernels that learn from data sparsity and hardware configurations.
“I am very excited to receive this career-boosting award,” Azad said. “Over the past few years, I have been closely working with two DOE national laboratories (Lawrence Berkeley National Lab and Pacific Northwest National Laboratory) on two exascale computing projects,” Azad said. “This award will support our research team to establish an even stronger collaboration with DOE labs and help us contribute to the science of national priorities.”
The project will also develop flexible and interpretable algorithms for graph embedding and graph neural networks that, in turn, rely on intelligent primitives for performance to solve exascale problems from metagenomics, scientific computing, and graph machine learning.
“Unlike other branches of artificial intelligence, graph machine learning is more exciting and challenging because it deals with unstructured and heterogeneous data,” Azad said. “Our next step is to make graph ML scalable to the limit of modern supercomputers, portable to all computing platforms including CPUs, GPUs, and supercomputers, and usable for diverse scientific applications from biology, chemistry, earth science, and data analytics.”
Azad was one of just 83 researchers throughout the nation to receive the award.
“Maintaining our nation’s brain trust of world-class scientists and researchers is one of DOE’s top priorities—and that means we need to give them the resources they need to succeed early on in their careers,” Secretary of Energy Jennifer M. Granholm said. “These awardees show exceptional potential to help us tackle America’s toughest challenges and secure our economic competitiveness for decades to come.”
Awardees of the grant included 32 researchers from the DOE’s national laboratories and 51 U.S. universities.
“Constantly pushing the boundaries of what is possible and developing new methods to interpret data is a core mission of the researchers at our school,” said Dennis Groth, interim dean of the Luddy School. “This prestigious award is tangible recognition of the importance of Ariful’s work, and we congratulate him for receiving this honor.”