English
Related papers

Related papers: Group Invariant Global Pooling

200 papers

The dynamics of the subatomic fundamental particles, represented by quantum fields, and their interactions are determined uniquely by the assigned transformation properties, i.e., the quantum numbers associated with the underlying symmetry…

High Energy Physics - Phenomenology · Physics 2020-10-28 Upalaparna Banerjee , Joydeep Chakrabortty , Suraj Prakash , Shakeel Ur Rahaman

Functions which are equivariant or invariant under the transformations of a compact linear group $G$ acting in an euclidean space $\real^n$, can profitably be studied as functions defined in the orbit space of the group. The orbit space is…

Mathematical Physics · Physics 2009-11-10 G. Sartori , G. Valente

Gaussian processes (GPs) are pervasive in functional data analysis, machine learning, and spatial statistics for modeling complex dependencies. Modern scientific data sets are typically heterogeneous and often contain multiple known…

Methodology · Statistics 2021-10-19 Didong Li , Andrew Jones , Sudipto Banerjee , Barbara E. Engelhardt

Hierarchical graph pooling(HGP) are designed to consider the fact that conventional graph neural networks(GNN) are inherently flat and are also not multiscale. However, most HGP methods suffer not only from lack of considering global…

Machine Learning · Computer Science 2025-04-14 Farshad Noravesh , Reza Haffari , Layki Soon , Arghya Pal

We present Orbit-Space Geometric Probability Paths (OGPP), a particle-native flow-matching framework for generative modeling of particle systems. OGPP is motivated by two insights: (i) particles are defined up to permutation symmetries, so…

Graphics · Computer Science 2026-05-05 Sinan Wang , Jinjin He , Shenyifan Lu , Ruicheng Wang , Greg Turk , Bo Zhu

Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we…

Machine Learning · Computer Science 2022-01-12 Zheng Ma , Junyu Xuan , Yu Guang Wang , Ming Li , Pietro Lio

For an Abelian surface $A$ with a symplectic action by a finite group $G$, one can define the partition function for $G$-invariant Hilbert schemes \[Z_{A, G}(q) = \sum_{d=0}^{\infty} e(\text{Hilb}^{d}(A)^{G})q^{d}.\] We prove the reciprocal…

Algebraic Geometry · Mathematics 2021-09-13 Stephen Pietromonaco

Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying different group actions, where standard techniques do not directly apply. We show that, when a group $G$ acts…

Machine Learning · Computer Science 2026-03-11 Alejandro García-Castellanos , Gijs Bellaard , Remco Duits , Daniel Pelt , Erik J Bekkers

Deep neural networks have achieved great success in the last decade. When designing neural networks to handle the ubiquitous geometric data such as point clouds and graphs, it is critical that the model can maintain invariance towards…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Ziwei Zhang , Xin Wang , Zeyang Zhang , Peng Cui , Wenwu Zhu

Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the…

Machine Learning · Computer Science 2020-02-04 Ekagra Ranjan , Soumya Sanyal , Partha Pratim Talukdar

Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation…

Computer Vision and Pattern Recognition · Computer Science 2021-06-02 Chen Zhao , Jiaqi Yang , Xin Xiong , Angfan Zhu , Zhiguo Cao , Xin Li

Deep Gaussian processes (DGPs), a hierarchical composition of GP models, have successfully boosted the expressive power of their single-layer counterpart. However, it is impossible to perform exact inference in DGPs, which has motivated the…

Machine Learning · Computer Science 2021-05-27 Haibin Yu , Dapeng Liu , Yizhou Chen , Bryan Kian Hsiang Low , Patrick Jaillet

Graph pooling is a family of operations which take graphs as input and produce shrinked graphs as output. Modern graph pooling methods are trainable and, in general inserted in Graph Neural Networks (GNNs) architectures as graph shrinking…

Machine Learning · Computer Science 2024-12-05 Yizhu Chen

Orbit harmonics is a tool in combinatorial representation theory which promotes the (ungraded) action of a linear group $G$ on a finite set $X$ to a graded action of $G$ on a polynomial ring quotient by viewing $X$ as a $G$-stable point…

Combinatorics · Mathematics 2020-10-19 Jaeseong Oh , Brendon Rhoades

Graph pooling has gained attention for its ability to obtain effective node and graph representations for various downstream tasks. Despite the recent surge in graph pooling approaches, there is a lack of standardized experimental settings…

Machine Learning · Computer Science 2026-04-03 Pengyun Wang , Junyu Luo , Yanxin Shen , Ming Zhang , Shaoen Qin , Hanwen Xing , Siyu Heng , Xiao Luo

Recent results in geometric invariant theory (GIT) for non-reductive linear algebraic group actions allow us to stratify quotient stacks of the form [X/H], where X is a projective scheme and H is a linear algebraic group with internally…

Algebraic Geometry · Mathematics 2017-11-29 Gergely Bérczi , Victoria Hoskins , Frances Kirwan

We give a polynomial gluing construction of two groups $G_X\subseteq GL(\ell,\mathbb F)$ and $G_Y\subseteq GL(m,\mathbb F)$ which results in a group $G\subseteq GL(\ell+m,\mathbb F)$ whose ring of invariants is isomorphic to the tensor…

Commutative Algebra · Mathematics 2011-12-13 Jia Huang

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Shaoyan Sun , Dacheng Tao

Group convolution works well with many deep convolutional neural networks (CNNs) that can effectively compress the model by reducing the number of parameters and computational cost. Using this operation, feature maps of different group…

Computer Vision and Pattern Recognition · Computer Science 2019-06-11 Xukai Xie , Yuan Zhou , Sun-Yuan Kung

We introduce G{\aa}rding polynomials, a class of real multivariate polynomials characterized by positivity regions that are invariant under translation by positive vectors and closed under strictly positive affine transformations. We prove…

Combinatorics · Mathematics 2026-05-19 Hao Fang , Biao Ma