LiftGCN improves finite element stress predictions with efficient graph learning
LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction
Machine LearningArtificial Intelligence
Summary
Predicting how parts stretch or bend under pressure is hard because sharp changes in stress happen near holes or cracks. Traditional graph neural networks smooth out these sharp changes, missing important details. The authors propose LiftGCN, a new method that preserves these sharp edges in the data efficiently. It does this by using a clever math trick called Joukowski spectral lifting, which keeps important signal frequencies while being computationally faster. Their tests show it predicts stress more accurately near complicated areas and does so with less computing power.
What this means in practice
- •For mechanical engineers: Improve the accuracy of finite element stress field predictions near sharp features with reduced computational cost.
- •For software developers for engineering simulations: Integrate LiftGCN to enhance graph-based neural networks that work on irregular mesh data for faster stress analysis.
Authors
Chen Zeng, Qiao Wang
Abstract
Finite element stress fields often exhibit strong local non-smoothness, where stress concentrations near holes, notches, and loading regions induce sharp spatial gradients and high-frequency graph components. Although graph neural networks naturally operate on irregular finite element meshes, conventional message passing is inherently smoothing and progressively attenuates such high-frequency information. Unitary propagation alleviates this problem by preserving spectral magnitudes, but typically relies on matrix functions and high-order approximations with $O(Ked)$ propagation complexity. We propose LiftGCN, an efficient spectrally stable graph network based on Joukowski spectral lifting. LiftGCN maps the real spectrum of a normalized graph operator onto the unit circle through the Joukowski relation and realizes the resulting spectral transformation as a simple second-order recurrence, avoiding matrix exponentials, eigendecomposition, and high-order polynomial truncation. We show that the linear Joukowski backbone has unit-modulus characteristic roots and admits an energy-preserving structure under a positive-definite metric, preventing exponential attenuation of graph-frequency components with depth. Each layer requires only one sparse neighborhood aggregation, yielding $O(ed)$ propagation complexity, while lightweight local nonlinear residuals provide expressive feature transformations. Experiments on finite element stress prediction demonstrate that LiftGCN achieves competitive overall accuracy while improving reconstruction of stress concentrations and local high-gradient structures with substantially reduced computational cost. Our code is available at https://github.com/ChenZeng001/LiftGCN.