Deep Learning for Graph Isomorphism: Theories and Applications

图同构的深度学习：理论与应用

• 批准号: DP210102273
• 负责人: Prof Brendan McKay
• 金额: $ 28.64万
• 依托单位: The Australian National University
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2022
• 资助国家: 澳大利亚
• 起止时间: 2022-01-01 至 2024-12-31
• 项目状态: 已结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP210102273
• 关键词: Deep; Learning; Graph; Isomorphism; Theories

This project aims to investigate graph isomorphism, a fundamental problem in graph theory, using deep learning techniques. Solutions to graph isomorphism are in demand by researchers in many fields of science, such as biology, chemistry, computer science, and quantum computing. The project expects to advance knowledge about graph isomorphism and state-of-the-art methodologies for its applications. The expected outcomes include new theoretical insights on combinatorial structures of graphs, efficient heuristic techniques for (maximum) subgraph isomorphism, and structured representation learning. The project should provide significant benefits to research in a wide range of science fields, as well as many real-world applications.

该项目旨在使用深度学习技术研究图同构，这是图论中的一个基本问题。图同构的解决方案是许多科学领域的研究人员所需要的，例如生物学，化学，计算机科学和量子计算。该项目预计将推进有关图同构及其应用的最先进方法的知识。预期的成果包括新的理论见解的组合结构的图，有效的启发式技术（最大）子图同构，和结构化表示学习。该项目将为广泛的科学领域的研究以及许多现实世界的应用提供显着的好处。