CAREER: New Frontiers in Graph Generation

职业：图生成的新领域

• 批准号: 2239869
• 负责人: Liping Liu
• 金额: $ 55.64万
• 依托单位: Tufts University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-01 至 2028-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2239869&HistoricalAwards=false
• 关键词: CAREER; New; Frontiers; Graph; Generation

A graph is a model of many different types of connections, relationships, or networks between different entities. It can be used to represent micro-level objects, like molecules being recorded as bonds connecting atoms, and macro-level networks, like social networks consisting of connections between users. Graph structures often contain rich information and are large in scale. An important task is to synthesize new graphs that are similar to but different from existing ones. For example, a drug design task may require a model to generate new molecule graphs for screening; and a data-sharing task for a social network may need a model to synthesize and share a graph similar to the original network, without releasing sensitive link information. This project combines neural networks and probabilistic methods to develop tools for generating new graphs for a wide range of tasks. These tools also have a solid statistical foundation and help to deepen the understanding of graph data.This project will advocate a new direction of developing graph generative models based on discrete sequential processes—the generative model starts from a random or trivial graph and tailors it in multiple steps to generate a random graph. The research effort in this project has three technical aims. First, the project will develop a probabilistic framework for building graph generative models with neural networks. Second, the project will overcome efficiency issues in model training and model predictions. Third, the project will compare newly developed models with traditional random graph models to deepen the understanding of network data. From the comparison, new methods will also be developed to preserve private information in the sharing of network data. Models to be developed from this project will have a solid statistical foundation and be connected to traditional random graph models.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.

图是不同实体之间许多不同类型的连接，关系或网络的模型。它可以用来表示微级对象，例如被记录为连接原子的债券的分子和宏观网络，例如由用户之间的连接组成的社交网络。图结构通常包含丰富的信息，并且规模较大。一个重要的任务是合成与现有图相似但不同的新图。例如，药物设计任务可能需要模型来生成用于筛选的新分子图。社交网络的数据共享任务可能需要一个模型来综合和共享类似于原始网络的图形，而无需发布敏感的链接信息。该项目结合了神经网络和概率方法，以开发用于为各种任务生成新图形的工具。这些工具还具有坚实的统计基础，并有助于加深对图形数据的理解。本项目将主张基于离散的顺序过程开发图形通用模型的新方向 - 通用模型从随机或琐碎的图形开始，并以多个步骤调整它以生成随机图。该项目的研究工作具有三个技术目标。首先，该项目将开发一个概率框架，用于使用神经网络构建图形通用模型。其次，该项目将克服模型培训和模型预测中的效率问题。第三，该项目将将新开发的模型与传统随机图模型进行比较，以加深对网络数据的理解。从比较中，还将开发新的方法来保存网络数据共享中的私人信息。从该项目开发的模型将具有坚实的统计基础，并与传统的随机图模型相连。该奖项反映了NSF的法定任务，并通过使用基金会的知识分子优点和更广泛的影响评估标准来评估值得支持。

项目成果

On Separate Normalization in Self-supervised Transformers

• DOI: 10.48550/arxiv.2309.12931
• 发表时间: 2023-09
• 期刊: ArXiv
• 作者: Xiaohui Chen;Yinkai Wang;Yuanqi Du;S. Hassoun;Liping Liu

Fitting Autoregressive Graph Generative Models through Maximum Likelihood Estimation

• 发表时间: 2023
• 期刊: J. Mach. Learn. Res.
• 作者: Xuhong Han;Xiaohui Chen;Francisco J. R. Ruiz;Liping Liu

Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling

• DOI: 10.48550/arxiv.2305.04111
• 发表时间: 2023-05
• 期刊: ArXiv
• 作者: Xiaohui Chen;Jiaxing He;Xuhong Han;Liping Liu

Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model

用顺序流生成模型统一网格缩减空间中确定性和随机物理的预测

• 发表时间: 2023
• 期刊: Advances in Neural Information Processing Systems 36
• 作者: Sun, Luning;Han, Xu;Gao, Han;Wang, Jian-Xun;Liu, Li-Ping
• 通讯作者: Liu, Li-Ping