paper-with-me

Papers

Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes

2020-11-25 · Peter Holderrieth, Michael Hutchinson, Yee Whye Teh

Motivated by objects such as electric fields or fluid streams, we study the problem of learning stochastic fields, i.e. stochastic processes whose samples are fields like those occurring in physics and engineering. Considering general transformations such as rotations and reflections, we show that spatial invariance of stochastic fields requires an inference model to be equivariant. Leveraging recent advances from the equivariance literature, we study equivariance in two classes of models. Firstly, we fully characterise equivariant Gaussian processes. Secondly, we introduce Steerable Conditional Neural Processes (SteerCNPs), a new, fully equivariant member of the Neural Process family. In experiments with Gaussian process vector fields, images, and real-world weather data, we observe that SteerCNPs significantly improve the performance of previous models and equivariance leads to improvements in transfer learning tasks.

📄 PDF Abstract BibTeX arXiv:2011.12916

Code (1)

anonymous-code-0/SteerableCNP 공식 구현 pytorch

Tasks

Gaussian ProcessesTransfer Learning

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

2018-07-06 · NeurIPS 2018 12 · Maurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma 외

We present a convolutional network that is equivariant to rigid body motions. The model uses scalar-, vector-, and tensor fields over 3D Euclidean space to represent data, and equivariant convolutions to map between such…

General Classification

Geometric and Physical Quantities Improve E(3) Equivariant Message Passing

2021-10-06 · ICLR 2022 4 · Johannes Brandstetter, Rob Hesselink, Elise van der Pol, Erik J Bekkers 외

Including covariant information, such as position, force, velocity or spin is important in many tasks in computational physics and chemistry. We introduce Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that ge…

Graph Property Prediction

Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)

2018-03-28 · Taco S. Cohen, Mario Geiger, Maurice Weiler

Group equivariant and steerable convolutional neural networks (regular and steerable G-CNNs) have recently emerged as a very effective model class for learning from signal data such as 2D and 3D images, video, and other …

Clifford-Steerable Convolutional Neural Networks

2024-02-22 · Maksim Zhdanov, David Ruhe, Maurice Weiler, Ana Lucic 외

We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, f…

Steerable Partial Differential Operators for Equivariant Neural Networks

2021-06-18 · ICLR 2022 4 · Erik Jenner, Maurice Weiler

Recent work in equivariant deep learning bears strong similarities to physics. Fields over a base space are fundamental entities in both subjects, as are equivariant maps between these fields. In deep learning, however, …

Deep Learning