Timezone: »

 
Poster
Generative Adversarial Symmetry Discovery
Jianke Yang · Robin Walters · Nima Dehmamy · Rose Yu

Wed Jul 26 02:00 PM -- 03:30 PM (PDT) @ Exhibit Hall 1 #703
in Poster Session 3 »
Event URL: https://github.com/Rose-STL-Lab/LieGAN »
Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry to use as an inductive bias in practice. Enforcing the wrong symmetry could even hurt the performance. In this paper, we propose a framework, LieGAN, to *automatically discover equivariances* from a dataset using a paradigm akin to generative adversarial training. Specifically, a generator learns a group of transformations applied to the data, which preserve the original distribution and fool the discriminator. LieGAN represents symmetry as interpretable Lie algebra basis and can discover various symmetries such as the rotation group $\mathrm{SO}(n)$, restricted Lorentz group $\mathrm{SO}(1,3)^+$ in trajectory prediction and top-quark tagging tasks. The learned symmetry can also be readily used in several existing equivariant neural networks to improve accuracy and generalization in prediction.
[ PDF] 

Author Information

Jianke Yang (University of California, San Diego)
Robin Walters (Northeastern University)
Nima Dehmamy (MIT-IBM Lab)

Physicist working on equivariant neural networks, Symmetries of the loss landscape, graph neural networks, and computational social science.

Rose Yu (University of California, San Diego)
Rose Yu

Dr. Rose Yu is an assistant professor at the University of California San Diego, Department of Computer Science and Engineering. She earned her Ph.D. in Computer Sciences at USC in 2017. She was subsequently a Postdoctoral Fellow at Caltech. 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 NSF CAREER Award, Faculty Research Award from JP Morgan, Facebook, Google, Amazon, and Adobe, Several Best Paper Awards, Best Dissertation Award at USC, and was nominated as one of the ’MIT Rising Stars in EECS’.

More from the Same Authors