Timezone: »
Incorporating symmetry as an inductive bias into neural network architecture has led to improvements in generalization, data efficiency, and physical consistency in dynamics modeling. Methods such as CNNs or equivariant neural networks use weight tying to enforce symmetries such as shift invariance or rotational equivariance. However, despite the fact that physical laws obey many symmetries, real-world dynamical data rarely conforms to strict mathematical symmetry either due to noisy or incomplete data or to symmetry breaking features in the underlying dynamical system. We explore approximately equivariant networks which are biased towards preserving symmetry but are not strictly constrained to do so. By relaxing equivariance constraints, we find that our models can outperform both baselines with no symmetry bias and baselines with overly strict symmetry in both simulated turbulence domains and real-world multi-stream jet flow.
Author Information
Rui Wang (University of California, San Diego)
Robin Walters (Northeastern University)
Rose Yu (University of California, San Diego)

Dr. Rose Yu is an assistant professor at the UC San Diego, Department of Computer Science and Engineering. Her research focuses on advancing machine learning techniques for large-scale spatiotemporal data analysis, with applications to sustainability, health, and physical sciences. A particular emphasis of her research is on physics-guided AI which aims to integrate first principles with data-driven models. Among her awards, she has won Faculty Research Award from Facebook, Google, Amazon, and Adobe, several Best Paper Awards, and the Best Dissertation Award in USC.
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Spotlight: Approximately Equivariant Networks for Imperfectly Symmetric Dynamics »
Tue. Jul 19th 08:30 -- 08:35 PM Room Room 327 - 329
More from the Same Authors
-
2022 : Data Augmentation vs. Equivariant Networks: A Theoretical Study of Generalizability on Dynamics Forecasting »
Rui Wang · Robin Walters · Rose Yu -
2022 Poster: Toward Compositional Generalization in Object-Oriented World Modeling »
Linfeng Zhao · Lingzhi Kong · Robin Walters · Lawson Wong -
2022 Oral: Toward Compositional Generalization in Object-Oriented World Modeling »
Linfeng Zhao · Lingzhi Kong · Robin Walters · Lawson Wong -
2022 Poster: LIMO: Latent Inceptionism for Targeted Molecule Generation »
Peter Eckmann · Kunyang Sun · Bo Zhao · Mudong Feng · Michael Gilson · Rose Yu -
2022 Poster: Learning Symmetric Embeddings for Equivariant World Models »
Jung Yeon Park · Ondrej Biza · Linfeng Zhao · Jan-Willem van de Meent · Robin Walters -
2022 Spotlight: Learning Symmetric Embeddings for Equivariant World Models »
Jung Yeon Park · Ondrej Biza · Linfeng Zhao · Jan-Willem van de Meent · Robin Walters -
2022 Spotlight: LIMO: Latent Inceptionism for Targeted Molecule Generation »
Peter Eckmann · Kunyang Sun · Bo Zhao · Mudong Feng · Michael Gilson · Rose Yu -
2021 : RL + Robotics Panel »
George Konidaris · Jan Peters · Martin Riedmiller · Angela Schoellig · Rose Yu · Rupam Mahmood -
2020 Poster: Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis »
Jung Yeon Park · Kenneth Carr · Stephan Zheng · Yisong Yue · Rose Yu