skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 10:00 PM ET on Friday, December 8 until 2:00 AM ET on Saturday, December 9 due to maintenance. We apologize for the inconvenience.

Search for: All records

Creators/Authors contains: "Jia, Z."

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Graph Neural Networks (GNNs) are based on repeated aggregations of information from nodes’ neighbors in a graph. However, because nodes share many neighbors, a naive implementation leads to repeated and inefficient aggregations and represents significant computational overhead. Here we propose Hierarchically Aggregated computation Graphs (HAGs), a new GNN representation technique that explicitly avoids redundancy by managing intermediate aggregation results hierarchically and eliminates repeated computations and unnecessary data transfers in GNN training and inference. HAGs perform the same computations and give the same models/accuracy as traditional GNNs, but in a much shorter time due to optimized computations. To identify redundant computations, we introduce an accurate cost function and use a novel search algorithm to find optimized HAGs. Experiments show that the HAG representation significantly outperforms the standard GNN by increasing the end-to-end training throughput by up to 2.8× and reducing the aggregations and data transfers in GNN training by up to 6.3× and 5.6×, with only 0.1% memory overhead. Overall, our results represent an important advancement in speeding-up and scaling-up GNNs without any loss in model predictive performance. 
    more » « less
  2. null (Ed.)
  3. Glioblastoma ranks among the most lethal of primary brain malignancies, with glioblastoma stem cells (GSCs) at the apex of tumor cellular hierarchies. Here, to discover novel therapeutic GSC targets, we interrogated gene expression profiles from GSCs, differentiated glioblastoma cells (DGCs), and neural stem cells (NSCs), revealing EYA2 as preferentially expressed by GSCs. Targeting EYA2 impaired GSC maintenance and induced cell cycle arrest, apoptosis, and loss of self-renewal. EYA2 displayed novel localization to centrosomes in GSCs, and EYA2 tyrosine (Tyr) phosphatase activity was essential for proper mitotic spindle assembly and survival of GSCs. Inhibition of the EYA2 Tyr phosphatase activity, via genetic or pharmacological means, mimicked EYA2 loss in GSCs in vitro and extended the survival of tumor-bearing mice. Supporting the clinical relevance of these findings, EYA2 portends poor patient prognosis in glioblastoma. Collectively, our data indicate that EYA2 phosphatase function plays selective critical roles in the growth and survival of GSCs, potentially offering a high therapeutic index for EYA2 inhibitors. 
    more » « less