paper-with-me

Papers

Equivariance Discovery by Learned Parameter-Sharing

2022-04-07 · Raymond A. Yeh, Yuan-Ting Hu, Mark Hasegawa-Johnson, Alexander G. Schwing

Designing equivariance as an inductive bias into deep-nets has been a prominent approach to build effective models, e.g., a convolutional neural network incorporates translation equivariance. However, incorporating these inductive biases requires knowledge about the equivariance properties of the data, which may not be available, e.g., when encountering a new domain. To address this, we study how to discover interpretable equivariances from data. Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes. We propose to use the partition distance to empirically quantify the accuracy of the recovered equivariance. Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme. Empirically, we show that the approach recovers known equivariances, such as permutations and shifts, on sum of numbers and spatially-invariant data.

📄 PDF Abstract BibTeX arXiv:2204.03640

Code (1)

raymondyeh07/equivariance_discovery 공식 구현 pytorch

Tasks

Inductive BiasTranslation

Similar Papers 제목 키워드 기반

Precoder Learning by Leveraging Unitary Equivariance Property

2025-03-12 · Yilun Ge, Shuyao Liao, Shengqian Han, Chenyang Yang

Incorporating mathematical properties of a wireless policy to be learned into the design of deep neural networks (DNNs) is effective for enhancing learning efficiency. Multi-user precoding policy in multi-antenna system,…

Relaxing Equivariance Constraints with Non-stationary Continuous Filters

2022-04-14 · Tycho F. A. van der Ouderaa, David W. Romero, Mark van der Wilk

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 throu…

image-classificationImage Classification

Equivariance Through Parameter-Sharing

2017-02-27 · ICML 2017 8 · Siamak Ravanbakhsh, Jeff Schneider, Barnabas Poczos

We propose to study equivariance in deep neural networks through parameter symmetries. In particular, given a group $\mathcal{G}$ that acts discretely on the input and output of a standard neural network layer $\phi_{W}:…

Sensitivity

Meta-Learning Symmetries by Reparameterization

2020-07-06 · ICLR 2021 1 · Allan Zhou, Tom Knowles, Chelsea Finn

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.…

Meta-Learning

Learning Layer-wise Equivariances Automatically using Gradients

2023-09-21 · NeurIPS 2023 11

Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. However, symmetries provide fixed hard constraints on the functions a network can represent, need to be speci…