Timezone: »
Existing equivariant neural networks require prior knowledge of the symmetry group and discretization for continuous groups. We propose to work with Lie algebras (infinitesimal generators) instead of Lie groups. Our model, the Lie algebra convolutional network (L-conv) can automatically discover symmetries and does not require discretization of the group. We show that L-conv can serve as a building block to construct any group equivariant feedforward architecture. Both CNNs and Graph Convolutional Networks can be expressed as L-conv with appropriate groups. We discover direct connections between L-conv and physics: (1) group invariant loss generalizes field theory (2) Euler-Lagrange equation measures the robustness, and (3) equivariance leads to conservation laws and Noether current. These connections open up new avenues for designing more general equivariant networks and applying them to important problems in physical sciences.
Author Information
Nima Dehmamy (Northwestern University)
I obtained my PhD in physics on complex systems from Boston University in 2016. I did postdoc at Northeastern University working on 3D embedded graphs and graph neural networks. My current research is on physics-informed machine learning and computational social science.
Robin Walters (Northeastern University)
Yanchen Liu (Northeastern University)
Dashun Wang (Northwestern University)
Rose Yu (Northeastern University)
More from the Same Authors
-
2022 : Lyapunov Regularized Forecaster »
Rong Zheng · Rose Yu -
2022 : A Noether's theorem for gradient flow: Continuous symmetries of the architecture and conserved quantities of gradient flow »
Bo Zhao · Iordan Ganev · Robin Walters · Rose Yu · Nima Dehmamy -
2022 : Charting Flat Minima Using the Conserved Quantities of Gradient Flow »
Bo Zhao · Iordan Ganev · Robin Walters · Rose Yu · Nima Dehmamy -
2022 : Understanding Optimization Challenges when Encoding to Geometric Structures »
Babak Esmaeili · Robin Walters · Heiko Zimmermann · Jan-Willem van de Meent -
2022 : Image to Icosahedral Projection for $\mathrm{SO}(3)$ Object Reasoning from Single-View Images »
David Klee · Ondrej Biza · Robert Platt · Robin Walters -
2023 Poster: Equivariant Single View Pose Prediction Via Induced and Restriction Representations »
Owen Howell · David Klee · Ondrej Biza · Linfeng Zhao · Robin Walters -
2023 Poster: A General Theory of Correct, Incorrect, and Extrinsic Equivariance »
Dian Wang · Xupeng Zhu · Jung Yeon Park · Mingxi Jia · Guanang Su · Robert Platt · Robin Walters -
2023 Poster: Topological Obstructions and How to Avoid Them »
Babak Esmaeili · Robin Walters · Heiko Zimmermann · Jan-Willem van de Meent -
2023 Poster: Modeling Dynamics over Meshes with Gauge Equivariant Message Passing »
Jung Yeon Park · Lawson Wong · Robin Walters -
2022 Poster: Meta-Learning Dynamics Forecasting Using Task Inference »
Rui Wang · Robin Walters · Rose Yu -
2022 Poster: Symmetry Teleportation for Accelerated Optimization »
Bo Zhao · Nima Dehmamy · Robin Walters · Rose Yu -
2020 : 15 - Lie Algebra Convolutional Networks with Automatic Symmetry Extraction »
Nima Dehmamy -
2019 : Afternoon Coffee Break & Poster Session »
Heidi Komkov · Stanislav Fort · Zhaoyou Wang · Rose Yu · Ji Hwan Park · Samuel Schoenholz · Taoli Cheng · Ryan-Rhys Griffiths · Chase Shimmin · Surya Karthik Mukkavili · Philippe Schwaller · Christian Knoll · Yangzesheng Sun · Keiichi Kisamori · Gavin Graham · Gavin Portwood · Hsin-Yuan Huang · Paul Novello · Moritz Munchmeyer · Anna Jungbluth · Daniel Levine · Ibrahim Ayed · Steven Atkinson · Jan Hermann · Peter Grönquist · · Priyabrata Saha · Yannik Glaser · Lingge Li · Yutaro Iiyama · Rushil Anirudh · Maciej Koch-Janusz · Vikram Sundar · Francois Lanusse · Auralee Edelen · Jonas Köhler · Jacky H. T. Yip · jiadong guo · Xiangyang Ju · Adi Hanuka · Adrian Albert · Valentina Salvatelli · Mauro Verzetti · Javier Duarte · Eric Moreno · Emmanuel de Bézenac · Athanasios Vlontzos · Alok Singh · Thomas Klijnsma · Brad Neuberg · Paul Wright · Mustafa Mustafa · David Schmidt · Steven Farrell · Hao Sun -
2019 : Towards physics-informed deep learning for turbulent flow prediction »
Rose Yu -
2019 Poster: Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology »
Nima Dehmamy · Albert-Laszlo Barabasi · Rose Yu -
2019 Poster: NAOMI: Non-Autoregressive Multiresolution Sequence Imputation »
Yukai Liu · Rose Yu · Stephan Zheng · Eric Zhan · Yisong Yue