English
Related papers

Related papers: Equivariance with Learned Canonicalization Functio…

200 papers

Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate and robust predictions. However, redesigning each component…

Machine Learning · Computer Science 2023-10-31 Arnab Kumar Mondal , Siba Smarak Panigrahi , Sékou-Oumar Kaba , Sai Rajeswar , Siamak Ravanbakhsh

In many applications, we desire neural networks to exhibit invariance or equivariance to certain groups due to symmetries inherent in the data. Recently, frame-averaging methods emerged to be a unified framework for attaining symmetries…

Machine Learning · Computer Science 2024-11-05 George Ma , Yifei Wang , Derek Lim , Stefanie Jegelka , Yisen Wang

Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural networks by mapping each input to a standard form. Yet, it often introduces discontinuities that can affect stability during training,…

Machine Learning · Computer Science 2026-04-17 Ya-Wei Eileen Lin , Ron Levie

This work introduces a novel approach to achieving architecture-agnostic equivariance in deep learning, particularly addressing the limitations of traditional layerwise equivariant architectures and the inefficiencies of the existing…

Machine Learning · Computer Science 2024-11-18 Siba Smarak Panigrahi , Arnab Kumar Mondal

Equivariant neural networks offer strong inductive biases for learning from molecular and geometric data but often rely on specialized, computationally expensive tensor operations. We present a framework to transfers existing tensor field…

Machine Learning · Computer Science 2025-10-01 Gerrit Gerhartz , Peter Lippmann , Fred A. Hamprecht

Canonicalization provides an architecture-agnostic method for enforcing equivariance, with generalizations such as frame-averaging recently gaining prominence as a lightweight and flexible alternative to equivariant architectures. Recent…

Machine Learning · Computer Science 2024-06-19 Nadav Dym , Hannah Lawrence , Jonathan W. Siegel

Robotic manipulation systems are increasingly deployed across diverse domains. Yet existing multi-modal learning frameworks lack inherent guarantees of geometric consistency, struggling to handle spatial transformations such as rotations…

Robotics · Computer Science 2025-11-20 Jian Deng , Yuandong Wang , Yangfu Zhu , Tao Feng , Tianyu Wo , Zhenzhou Shao

Many machine learning models leverage group invariance which is enjoyed with a wide-range of applications. For exploiting an invariance structure, one common approach is known as \emph{frame averaging}. One popular example of frame…

Machine Learning · Computer Science 2025-09-23 Wee Chaimanowong , Ying Zhu

Incorporating group symmetries via equivariance into neural networks has emerged as a robust approach for overcoming the efficiency and data demands of modern deep learning. While most existing approaches, such as group convolutions and…

Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The existing generative modeling paradigm for invariant densities combines an invariant prior with an…

Machine Learning · Computer Science 2026-04-14 Kusha Sareen , Daniel Levy , Arnab Kumar Mondal , Sékou-Oumar Kaba , Tara Akhound-Sadegh , Siamak Ravanbakhsh

Symmetric functions, which take as input an unordered, fixed-size set, are known to be universally representable by neural networks that enforce permutation invariance. These architectures only give guarantees for fixed input sizes, yet in…

Machine Learning · Computer Science 2022-10-11 Aaron Zweig , Joan Bruna

We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use an arbitrary base model such as an MLP or a transformer and…

Machine Learning · Computer Science 2024-04-16 Jinwoo Kim , Tien Dat Nguyen , Ayhan Suleymanzade , Hyeokjun An , Seunghoon Hong

Many successful deep learning architectures are equivariant to certain transformations in order to conserve parameters and improve generalization: most famously, convolution layers are equivariant to shifts of the input. This approach only…

Machine Learning · Computer Science 2021-03-31 Allan Zhou , Tom Knowles , Chelsea Finn

Convolutional neural networks have been extremely successful in the image recognition domain because they ensure equivariance to translations. There have been many recent attempts to generalize this framework to other domains, including…

Machine Learning · Statistics 2018-11-13 Risi Kondor , Shubhendu Trivedi

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 constraints such as…

Machine Learning · Computer Science 2026-02-17 Cai Zhou , Zijie Chen , Zian Li , Jike Wang , Kaiyi Jiang , Pan Li , Rose Yu , Muhan Zhang , Stephen Bates , Tommi Jaakkola

While invariant architectures are standard for processing symmetric data, there is growing interest in achieving invariance by applying group averaging or canonization to non-invariant backbones. However, the theoretical generalization…

Machine Learning · Computer Science 2026-05-13 Yonatan Sverdlov , Benjamin Friedman , Snir Hordan , Nadav Dym

Conventional neural networks are universal function approximators, but because they are unaware of underlying symmetries or physical laws, they may need impractically many training data to approximate nonlinear dynamics. Recently introduced…

Machine Learning · Computer Science 2020-10-30 Anshul Choudhary , John F. Lindner , Elliott G. Holliday , Scott T. Miller , Sudeshna Sinha , William L. Ditto

Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as…

Machine Learning · Computer Science 2025-11-19 Erkao Bao , Jingcheng Lu , Linqi Song , Nathan Hart-Hodgson , William Parson , Yanheng Zhou

Neural networks that process the parameters of other neural networks find applications in domains as diverse as classifying implicit neural representations, generating neural network weights, and predicting generalization errors. However,…

An important goal in visual recognition is to devise image representations that are invariant to particular transformations. In this paper, we address this goal with a new type of convolutional neural network (CNN) whose invariance is…

Computer Vision and Pattern Recognition · Computer Science 2015-01-08 Julien Mairal , Piotr Koniusz , Zaid Harchaoui , Cordelia Schmid
‹ Prev 1 2 3 10 Next ›