Spatiotemporal Learning on Cell-embedded Graphs

📅 2024-09-26
🏛️ arXiv.org
📈 Citations: 1
Influential: 0
📄 PDF

career value

211K/year
🤖 AI Summary
Existing grid-based graph neural networks (GNNs) are constrained by first-order node-edge message passing, limiting their ability to capture high-order spatial dependencies among regional features and voxel-level geometric information in physical systems. Method: We propose the Cell-embedded Graph Neural Network (CeGNN), which introduces a novel learnable cell-attribute embedding mechanism that extends message passing from “edge→node” to “cell→edge→node”, explicitly encoding local geometric structure; additionally, we design a basis-function-driven feature enhancement module that mitigates over-smoothing by leveraging implicit features as functional bases. Contribution/Results: Evaluated on diverse PDE-solving tasks and real-world physical datasets, CeGNN consistently outperforms state-of-the-art GNN baselines, achieving up to an order-of-magnitude reduction in prediction error. This work establishes a new paradigm for data-driven physics simulation—uniquely balancing expressive power with geometric awareness.

Technology Category

Application Category

📝 Abstract
Data-driven simulation of physical systems has recently kindled significant attention, where many neural models have been developed. In particular, mesh-based graph neural networks (GNNs) have demonstrated significant potential in predicting spatiotemporal dynamics across arbitrary geometric domains. However, the existing node-edge message passing mechanism in GNNs limits the model's representation learning ability. In this paper, we proposed a cell-embedded GNN model (aka CeGNN) to learn spatiotemporal dynamics with lifted performance. Specifically, we introduce a learnable cell attribution to the node-edge message passing process, which better captures the spatial dependency of regional features. Such a strategy essentially upgrades the local aggregation scheme from the first order (e.g., from edge to node) to a higher order (e.g., from volume to edge and then to node), which takes advantage of volumetric information in message passing. Meanwhile, a novel feature-enhanced block is designed to further improve the performance of CeGNN and relieve the over-smoothness problem, via treating the latent features as basis functions. The extensive experiments on various PDE systems and one real-world dataset demonstrate that CeGNN achieves superior performance compared with other baseline models, particularly reducing the prediction error with up to 1 orders of magnitude on several PDE systems.
Problem

Research questions and friction points this paper is trying to address.

Enhancing GNN representation learning for spatiotemporal dynamics modeling
Upgrading local aggregation from first-order to higher-order volumetric passing
Addressing over-smoothness through novel feature-enhanced block design
Innovation

Methods, ideas, or system contributions that make the work stand out.

Embedding learnable cell attributions in message passing
Upgrading local aggregation to higher-order volumetric scheme
Designing feature-enhanced block to prevent over-smoothing
🔎 Similar Papers
No similar papers found.