English
Related papers

Related papers: Improving Equivariant Networks with Probabilistic …

200 papers

Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…

Machine Learning · Computer Science 2025-11-13 Ege Erdogan , Ana Lucic

Cycles are fundamental elements in graph-structured data and have demonstrated their effectiveness in enhancing graph learning models. To encode such information into a graph learning framework, prior works often extract a summary quantity,…

Machine Learning · Computer Science 2023-12-01 Zuoyu Yan , Tengfei Ma , Liangcai Gao , Zhi Tang , Chao Chen , Yusu Wang

The introduction of convolutional layers greatly advanced the performance of neural networks on image tasks due to innately capturing a way of encoding and learning translation-invariant operations, matching one of the underlying symmetries…

Computer Vision and Pattern Recognition · Computer Science 2016-12-15 Nicholas Guttenberg , Nathaniel Virgo , Olaf Witkowski , Hidetoshi Aoki , Ryota Kanai

In recent years, deep learning techniques have shown great success in various tasks related to inverse problems, where a target quantity of interest can only be observed through indirect measurements by a forward operator. Common approaches…

Numerical Analysis · Mathematics 2024-03-18 Matthias Beckmann , Nick Heilenkötter

Simulation-based inference with conditional neural density estimators is a powerful approach to solving inverse problems in science. However, these methods typically treat the underlying forward model as a black box, with no way to exploit…

Machine Learning · Computer Science 2023-05-31 Maximilian Dax , Stephen R. Green , Jonathan Gair , Michael Deistler , Bernhard Schölkopf , Jakob H. Macke

While (message-passing) graph neural networks have clear limitations in approximating permutation-equivariant functions over graphs or general relational data, more expressive, higher-order graph neural networks do not scale to large…

Machine Learning · Computer Science 2022-08-31 Christopher Morris , Gaurav Rattan , Sandra Kiefer , Siamak Ravanbakhsh

Soft, porous mechanical metamaterials exhibit pattern transformations that may have important applications in soft robotics, sound reduction and biomedicine. To design these innovative materials, it is important to be able to simulate them…

Soft Condensed Matter · Physics 2025-03-14 Fleur Hendriks , Vlado Menkovski , Martin Doškář , Marc G. D. Geers , Ondřej Rokoš

Local gauge symmetry underlies fundamental interactions and strongly correlated quantum matter, yet existing machine-learning approaches lack a general, principled framework for learning under site-dependent symmetries, particularly for…

Strongly Correlated Electrons · Physics 2026-04-23 Ali Rayat , Yaohang Li , Gia-Wei Chern

Capsule networks are constrained by the parameter-expensive nature of their layers, and the general lack of provable equivariance guarantees. We present a variation of capsule networks that aims to remedy this. We identify that learning all…

Machine Learning · Computer Science 2019-09-27 Sairaam Venkatraman , S. Balasubramanian , R. Raghunatha Sarma

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

We present the Topology Transformation Equivariant Representation learning, a general paradigm of self-supervised learning for node representations of graph data to enable the wide applicability of Graph Convolutional Neural Networks…

Machine Learning · Computer Science 2021-12-03 Xiang Gao , Wei Hu , Guo-Jun Qi

We present group equivariant capsule networks, a framework to introduce guaranteed equivariance and invariance properties to the capsule network idea. Our work can be divided into two contributions. First, we present a generic routing by…

Computer Vision and Pattern Recognition · Computer Science 2018-10-25 Jan Eric Lenssen , Matthias Fey , Pascal Libuschewski

Network Embeddings (NEs) map the nodes of a given network into $d$-dimensional Euclidean space $\mathbb{R}^d$. Ideally, this mapping is such that `similar' nodes are mapped onto nearby points, such that the NE can be used for purposes such…

Machine Learning · Statistics 2018-10-17 Bo Kang , Jefrey Lijffijt , Tijl De Bie

We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which…

Machine Learning · Computer Science 2022-10-04 Derek Lim , Joshua Robinson , Lingxiao Zhao , Tess Smidt , Suvrit Sra , Haggai Maron , Stefanie Jegelka

The translation equivariance of convolutions can make convolutional neural networks translation equivariant or invariant. Equivariance to other transformations (e.g. rotations, affine transformations, scalings) may also be desirable as soon…

Signal Processing · Electrical Eng. & Systems 2021-05-05 Mateus Sangalli , Samy Blusseau , Santiago Velasco-Forero , Jesus Angulo

We study distribution-free predictive inference for data with group symmetries, aiming to establish near-conditional coverage guarantees beyond exchangeability for structured data. While many predictive inference methods achieve a target…

Methodology · Statistics 2026-05-19 Yichen Shen , Mengxin Yu

Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for…

Robotics · Computer Science 2024-08-27 Hai Nguyen , Andrea Baisero , David Klee , Dian Wang , Robert Platt , Christopher Amato

Metanetworks are neural architectures designed to operate directly on pretrained weights to perform downstream tasks. However, the parameter space serves only as a proxy for the underlying function class, and the parameter-function mapping…

Machine Learning · Computer Science 2026-04-28 Viet-Hoang Tran , An Nguyen , Benoît Guérand , Thieu N. Vo , Tan M. Nguyen

At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…

Machine Learning · Computer Science 2024-05-29 Sharut Gupta , Chenyu Wang , Yifei Wang , Tommi Jaakkola , Stefanie Jegelka

Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent in physics. These…

Machine Learning · Computer Science 2025-12-17 Sophia Tang