主题：DP-PINN+: A Dual Phase PINN Training with Automated Phase Division

嘉宾：何黎刚 华威大学计算机系 Reader

时间：2025年8月14日 下午15:00-16:00

地点：华中科技大学东五楼210学术报告厅

报告摘要：

Physics-Informed Neural Networks (PINNs) are a promising application of deep neural networks for the numerical solution of nonlinear partial differential equations (PDEs). However, it has been observed that standard PINNs may not be able to accurately fit all types of PDEs, leading to poor predictions for specific regions in the domain. A common solution is to partition the domain by time and train each time interval separately. However, this approach leads to the prediction errors being accumulated over time, which is especially the case when solving “stiff” PDEs. To address these issues, we propose a new PINN training scheme, called DP-PINN+ (Dual-Phase PINN). DP-PINN+ divides the training into two phases based on a carefully chosen time point t_s. The phase-1 training aims to generate the accurate solution at t_s, which will serve as the additional intermediate condition for the phase-2 training. New sampling strategies are also proposed to enhance the training process. Moreover, a novel approach is developed to divide two phases (i.e., determine the value of t_s) automatically. These design considerations improve the prediction accuracy significantly. The experimental results show that the solutions predicted by DP- PINN exhibit significantly higher accuracy compared to those obtained by the state-of-the-art PINNs in literature.

报告人简介：

何黎刚博士本科和硕士毕业于华中科技大学，博士毕业于英国华威大学计算机系，并在剑桥大学进行博士后研究。现为华威大学计算机系Reader。当前的研究方向包括并行或分布式机器/深度学习（例如联邦学习、图神经网络训练加速）、集群、云计算和边缘计算（例如，优化工作负载和资源管理解决方案）、并行化/分布式数据分析方法（例如，时间序列数据的异常检测、点云的深度学习方法、大数据的模式发现），以及并行与分布式系统中的杂项问题（例如，在分布式系统中优化通信方案、有安全约束的高性能计算）。ScholarGPS2024 榜单分布式计算领域全球前0.5%学者。在国际期刊和会议上（例如IEEE TC, TPDS, TKDE, TCSVT, NeurIPS, SC, ICDCS, IPDPS, ICPP, HPCA, EuroSys）发表论文200余篇，并且多次获得最佳论文奖（例如在联邦学习领域的论文获得2021年度IEEE Transactions on Computers期刊的最佳论文奖第二名）。主持和承担过英国、欧盟及企业界多个研究项目。