4 papers
Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks
Jing Xiao, Xinhai Chen, Qinglin Wang +5
Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients.…
Prior-Guided Symbolic Regression: Towards Scientific Consistency in Equation Discovery
Jing Xiao, Xinhai Chen, Jiaming Peng +7
Symbolic Regression (SR) aims to discover interpretable equations from observational data, with the potential to reveal underlying principles behind natural phenomena. However, exi…
UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss
Zhichao Wang, Xinhai Chen, Qinglin Wang +5
Partial differential equations (PDEs) form the mathematical foundation for modeling physical systems in science and engineering, where numerical solutions demand rigorous accuracy-…
State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend
Fei Cui, Jiaojiao Fang, Xiaojiang Wu +4
Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic vi…