Efficient and accurate scaling Graph Neural Networks for giant graphs

• Project/Area Number: 24K20787
• Research Category: Grant-in-Aid for Early-Career Scientists
• Allocation Type: Multi-year Fund
• Review Section: Basic Section 61010:Perceptual information processing-related
• Research Institution: The University of Tokyo
• Principal Investigator: 肖 玲 東京大学, 大学院情報理工学系研究科, 特任助教 (40946787)
• Project Period (FY): 2024-04-01 – 2026-03-31
• Project Status: Granted (Fiscal Year 2024)
• Budget Amount: ¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000); Fiscal Year 2025: ¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000); Fiscal Year 2024: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
• Keywords: Scalable Networks / Represnetation Learning / Prompt Engineering

Outline of Research at the Start

In this research, we aim to revolutionize the approach to processing giant graphs. Specifically, we consider leveraging large language and vision models to boost giant graph processing. Our goal is to propose novel knowledge mining techniques for giant graphs. We will also develop novel algorithms for continual learning, adversarial attacks, and interpretation to enhance the scalability and trustworthiness of our proposed method.