Skip directly to content

Minimize RSR Award Detail

Research Spending & Results

Award Detail

Awardee:IOWA STATE UNIVERSITY OF SCIENCE AND TECHNOLOGY
Doing Business As Name:Iowa State University
PD/PI:
  • Hongyang Gao
  • (708) 964-8907
  • hygao@iastate.edu
Award Date:05/06/2021
Estimated Total Award Amount: $ 175,000
Funds Obligated to Date: $ 175,000
  • FY 2021=$175,000
Start Date:07/01/2021
End Date:06/30/2023
Transaction Type:Grant
Agency:NSF
Awarding Agency Code:4900
Funding Agency Code:4900
CFDA Number:47.070
Primary Program Source:040100 NSF RESEARCH & RELATED ACTIVIT
Award Title or Description:CRII: III: Graph Neural Networks: A Feature and Structure Learning Approach
Federal Award ID Number:2104797
DUNS ID:005309844
Parent DUNS ID:005309844
Program:Info Integration & Informatics
Program Officer:
  • Amarda Shehu
  • (703) 292-8191
  • ashehu@nsf.gov

Awardee Location

Street:1138 Pearson
City:AMES
State:IA
ZIP:50011-2207
County:Ames
Country:US
Awardee Cong. District:04

Primary Place of Performance

Organization Name:Iowa State University
Street:1138 Pearson
City:Ames
State:IA
ZIP:50011-2103
County:Ames
Country:US
Cong. District:04

Abstract at Time of Award

Many data in the real world can be naturally represented by graphs, such as social networks, citation networks, chemical compounds, and biological networks. The graph structure is an effective way to express relationships among a collection of items. Using graphs to represent these data, we can obtain an advanced understanding of the complex data structures embedded in the raw data. Graph mining using machine learning methods yields many exciting discoveries in various fields. Existing graph deep learning methods, such as graph convolutional networks (GNN), conduct local information aggregation with local structural operations. They usually stack multiple graph convolutional layers to enable a larger receptive field, which is straightforward but can result in several issues, including over-fitting and over-smoothing. These issues are critical to graph neural networks but are not well investigated. The objective of this project is to develop advanced graph learning methods without going deep and complex. This project also facilitates integrating graph learning algorithms into existing curricula of Machine Learning courses at both undergraduate and graduate levels. Specifically, this project focuses on how to enlarge receptive fields without going deep effectively. This project develops a set of advanced convolution, pooling, and un-pooling operations on graphs. The advanced graph convolution layer utilizes teleport functions to select highly relevant nodes at the global scope. In this layer, a teleport function computes relevance between the center node and other nodes beyond the local neighborhood. The nodes with particular relevance are teleported for the center node, enabling the center node to gather information from a broader neighborhood. The new graph pooling layer uses an attention operation to produce a better-connected coarsened graph with more graph topology information. In particular, it leverages an attention operator to generate ranking scores for node selection, capturing the graph connectivity information. The proposed graph un-pooling layer utilizes an attention operator to initialize restored nodes. Altogether, this project provides a systematic GNN study on graph feature and structure learning and is expected to advance GNNs development significantly. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

For specific questions or comments about this information including the NSF Project Outcomes Report, contact us.