paper-with-me

Papers

Importance of equivariant and invariant symmetries for fluid flow modeling

2023-05-03 · Varun Shankar, Shivam Barwey, Zico Kolter, Romit Maulik, Venkatasubramanian Viswanathan

Graph neural networks (GNNs) have shown promise in learning unstructured mesh-based simulations of physical systems, including fluid dynamics. In tandem, geometric deep learning principles have informed the development of equivariant architectures respecting underlying physical symmetries. However, the effect of rotational equivariance in modeling fluids remains unclear. We build a multi-scale equivariant GNN to forecast fluid flow and study the effect of modeling invariant and non-invariant representations of the flow state. We evaluate the model performance of several equivariant and non-equivariant architectures on predicting the evolution of two fluid flows, flow around a cylinder and buoyancy-driven shear flow, to understand the effect of equivariance and invariance on data-driven modeling approaches. Our results show that modeling invariant quantities produces more accurate long-term predictions and that these invariant quantities may be learned from the velocity field using a data-driven encoder.

📄 PDF Abstract BibTeX arXiv:2307.05486

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Equivariant Manifold Flows

2021-03-08 · Anonymous

Tractably modelling distributions over manifolds has long been an important goal in the natural sciences. Recent work has focused on developing general machine learning models to learn such distributions. Though these ar…

Equivariant Manifold Neural ODEs and Differential Invariants

2024-01-25 · Emma Andersdotter, Daniel Persson, Fredrik Ohlsson

In this paper, we develop a manifestly geometric framework for equivariant manifold neural ordinary differential equations (NODEs) and use it to analyse their modelling capabilities for symmetric data. First, we consider…

Equivariant Manifold Flows

2021-07-19 · NeurIPS 2021 12 · Isay Katsman, Aaron Lou, Derek Lim, Qingxuan Jiang 외

Tractably modelling distributions over manifolds has long been an important goal in the natural sciences. Recent work has focused on developing general machine learning models to learn such distributions. However, for ma…

Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation

2026-02-16 · Cai Zhou, Zijie Chen, Zian Li, Jike Wang 외 arxiv

Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equivariance through architectural constraint…

Graph Generation

Equivariant Flows: Exact Likelihood Generative Learning for Symmetric Densities

2020-06-03 · Jonas Köhler, Leon Klein, Frank Noé

Normalizing flows are exact-likelihood generative neural networks which approximately transform samples from a simple prior distribution to samples of the probability distribution of interest. Recent work showed that suc…