Transformer with Implicit Edges for Particle-based Physics Simulation

2022/07/22 by Yidi Shao, Shao, Yidi, Chen Change Loy +3 · 4 citations
Computer Science · #Computational Physics and Python Applications #FOS: Computer and information sciences #Graphics (cs.GR) #Machine Learning (cs.LG) #Parallel Computing and Optimization Techniques #Topic Modeling #cs.GR #cs.LG

paper · pdf · doi:10.48550/arxiv.2207.10860

Accepted by ECCV2022, 14 pages

arxiv created 2022/07/22 · openalex publication_date 2022/07/22 · arxiv updated 2022/07/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Particle-based systems provide a flexible and unified way to simulate physics systems with complex dynamics. Most existing data-driven simulators for particle-based systems adopt graph neural networks (GNNs) as their network backbones, as particles and their interactions can be naturally represented by graph nodes and graph edges. However, while particle-based systems usually contain hundreds even thousands of particles, the explicit modeling of particle interactions as graph edges inevitably leads to a significant computational overhead, due to the increased number of particle interactions. Consequently, in this paper we propose a novel Transformer-based method, dubbed as Transformer with Implicit Edges (TIE), to capture the rich semantics of particle interactions in an edge-free manner. The core idea of TIE is to decentralize the computation involving pair-wise particle interactions into per-particle updates. This is achieved by adjusting the self-attention module to resemble the update formula of graph edges in GNN. To improve the generalization ability of TIE, we further amend TIE with learnable material-specific abstract particles to disentangle global material-wise semantics from local particle-wise semantics. We evaluate our model on diverse domains of varying complexity and materials. Compared with existing GNN-based methods, without bells and whistles, TIE achieves superior performance and generalization across all these domains. Codes and models are available at https://github.com/ftbabi/TIE_ECCV2022.git.

Cited by

• Unbinned measurement of thrust in e⁺e^- collisions at √(s) = 91.2 GeV with ALEPH archived data
• Reversible GNS for Dissipative Fluids with Consistent Bidirectional Dynamics
• FluidFormer: Transformer with Continuous Convolution for Particle-based Fluid Simulation
• FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation

Related

• Learning Physics-Consistent Particle Interactions
• Attention to the strengths of physical interactions: Transformer and graph-based event classification for particle physics experiments
• Learning to Simulate Complex Physics with Graph Networks
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
• WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer