English
Related papers

Related papers: Quasi-Equivariant Metanetworks

200 papers

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

Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction. Unfortunately, the unique symmetry structure of deep weight spaces makes this design very…

Machine Learning · Computer Science 2023-06-02 Aviv Navon , Aviv Shamsian , Idan Achituve , Ethan Fetaya , Gal Chechik , Haggai Maron

Neural networks efficiently encode learned information within their parameters. Consequently, many tasks can be unified by treating neural networks themselves as input data. When doing so, recent studies demonstrated the importance of…

Machine Learning · Computer Science 2024-01-02 Derek Lim , Haggai Maron , Marc T. Law , Jonathan Lorraine , James Lucas

This paper pertains to an emerging machine learning paradigm: learning higher-order functions, i.e. functions whose inputs are functions themselves, $\textit{particularly when these inputs are Neural Networks (NNs)}$. With the growing…

Machine Learning · Computer Science 2024-10-31 Ioannis Kalogeropoulos , Giorgos Bouritsas , Yannis Panagakis

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…

Machine Learning · Computer Science 2022-06-17 Rui Wang , Robin Walters , Rose Yu

Equivariances provide useful inductive biases in neural network modeling, with the translation equivariance of convolutional neural networks being a canonical example. Equivariances can be embedded in architectures through weight-sharing…

Machine Learning · Computer Science 2022-11-15 Tycho F. A. van der Ouderaa , David W. Romero , Mark van der Wilk

This work studies the design of neural networks that can process the weights or gradients of other neural networks, which we refer to as neural functional networks (NFNs). Despite a wide range of potential applications, including learned…

Machine Learning · Computer Science 2023-09-27 Allan Zhou , Kaien Yang , Kaylee Burns , Adriano Cardace , Yiding Jiang , Samuel Sokota , J. Zico Kolter , Chelsea Finn

We investigate the relation between end-to-end equivariance and layerwise equivariance in deep neural networks. We prove the following: For a network whose end-to-end function is equivariant with respect to group actions on the input and…

Machine Learning · Computer Science 2026-01-30 Vahid Shahverdi , Giovanni Luca Marchetti , Georg Bökman , Kathlén Kohn

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their separation power, that is, the ability to distinguish inputs…

Machine Learning · Computer Science 2026-02-04 Marco Pacini , Gabriele Santin , Bruno Lepri , Shubhendu Trivedi

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,…

Equivariant deep learning architectures exploit symmetries in learning problems to improve the sample efficiency of neural-network-based models and their ability to generalise. However, when modelling real-world data, learning problems are…

Machine Learning · Statistics 2024-11-12 Matthew Ashman , Cristiana Diaconu , Adrian Weller , Wessel Bruinsma , Richard E. Turner

Hypernetworks, or hypernets for short, are neural networks that generate weights for another neural network, known as the target network. They have emerged as a powerful deep learning technique that allows for greater flexibility,…

Machine Learning · Computer Science 2025-01-03 Vinod Kumar Chauhan , Jiandong Zhou , Ping Lu , Soheila Molaei , David A. Clifton

This work explores hypernetworks: an approach of using a one network, also known as a hypernetwork, to generate the weights for another network. Hypernetworks provide an abstraction that is similar to what is found in nature: the…

Machine Learning · Computer Science 2016-12-02 David Ha , Andrew Dai , Quoc V. Le

Quantum neural network architectures that have little-to-no inductive biases are known to face trainability and generalization issues. Inspired by a similar problem, recent breakthroughs in machine learning address this challenge by…

The crucial role played by the underlying symmetries of high energy physics and lattice field theories calls for the implementation of such symmetries in the neural network architectures that are applied to the physical system under…

High Energy Physics - Lattice · Physics 2022-02-16 Srinath Bulusu , Matteo Favoni , Andreas Ipp , David I. Müller , Daniel Schuh

This paper introduces a new Convolutional Neural Network (ConvNet) architecture inspired by a class of partial differential equations (PDEs) called quasi-linear hyperbolic systems. With comparable performance on the image classification…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yao Liu , Hang Shao , Bing Bai

Weight-space learning studies neural architectures that operate directly on the parameters of other neural networks. Motivated by the growing availability of pretrained models, recent work has demonstrated the effectiveness of weight-space…

Machine Learning · Computer Science 2026-02-03 Adir Dayan , Yam Eitan , Haggai Maron

The set of functions parameterized by a linear fully-connected neural network is a determinantal variety. We investigate the subvariety of functions that are equivariant or invariant under the action of a permutation group. Examples of such…

Machine Learning · Computer Science 2025-01-13 Kathlén Kohn , Anna-Laura Sattelberger , Vahid Shahverdi

Extensive work has demonstrated that equivariant neural networks can significantly improve sample efficiency and generalization by enforcing an inductive bias in the network architecture. These applications typically assume that the domain…

Machine Learning · Computer Science 2023-02-13 Dian Wang , Jung Yeon Park , Neel Sortur , Lawson L. S. Wong , Robin Walters , Robert Platt

How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the…

Computer Vision and Pattern Recognition · Computer Science 2019-05-28 Kai Sheng Tai , Peter Bailis , Gregory Valiant
‹ Prev 1 2 3 10 Next ›