Neural Network based Graph Learning: Model Evolution and Real-World Application

2023 Fiscal Year Final Research Report

• Project/Area Number: 21K12042
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 61030:Intelligent informatics-related
• Research Institution: National Institute of Advanced Industrial Science and Technology
• Principal Investigator: Liu Xin 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 主任研究員 (20803935)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Keywords: graph neural network / graph embedding / graph analysis / social network / complex network

Outline of Final Research Achievements

This project has resulted in many advances in graph learning techniques. We have designed new learning architectures that achieved remarkable performance improvement. We have developed new models for heterogeneous graphs. We have proposed new practical strategies for working in various imperfect environments. We have successfully applied our approaches to many real-world applications.

Free Research Field

知能情報学

Academic Significance and Societal Importance of the Research Achievements

Several intrinsic defects in the current graph learning technology have hindered its widespread success. This project addresses these defects and promotes advancements in graph learning models. Many of the ideas created in this project have already diffused in the academic and industry community.