English
Related papers

Related papers: Symmetry-driven graph neural networks

200 papers

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…

Incorporating Euclidean symmetries (e.g. rotation equivariance) as inductive biases into graph neural networks has improved their generalization ability and data efficiency in unbounded physical dynamics modeling. However, in various…

Machine Learning · Computer Science 2024-06-25 Zinan Zheng , Yang Liu , Jia Li , Jianhua Yao , Yu Rong

Interest has been rising lately towards methods representing data in non-Euclidean spaces, e.g. hyperbolic or spherical, that provide specific inductive biases useful for certain real-world data properties, e.g. scale-free, hierarchical or…

Machine Learning · Computer Science 2020-05-20 Gregor Bachmann , Gary Bécigneul , Octavian-Eugen Ganea

We investigate the optimization of neural networks on symmetric data, and compare the strategy of constraining the architecture to be equivariant to that of using data augmentation. Our analysis reveals that that the relative geometry of…

Machine Learning · Computer Science 2024-10-21 Oskar Nordenfors , Fredrik Ohlsson , Axel Flinth

Equivariance w.r.t. geometric transformations in neural networks improves data efficiency, parameter efficiency and robustness to out-of-domain perspective shifts. When equivariance is not designed into a neural network, the network can…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Robert-Jan Bruintjes , Tomasz Motyka , Jan van Gemert

We present a novel framework to overcome the limitations of equivariant architectures in learning functions with group symmetries. In contrary to equivariant architectures, we use an arbitrary base model such as an MLP or a transformer and…

Machine Learning · Computer Science 2024-04-16 Jinwoo Kim , Tien Dat Nguyen , Ayhan Suleymanzade , Hyeokjun An , Seunghoon Hong

State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are successful examples of…

Computer Vision and Pattern Recognition · Computer Science 2020-12-07 Carlos Esteves

By recursively summing node features over entire neighborhoods, spatial graph convolution operators have been heralded as key to the success of Graph Neural Networks (GNNs). Yet, despite the multiplication of GNN methods across tasks and…

Machine Learning · Computer Science 2022-07-14 Sowon Jeong , Claire Donnat

Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and can slow down…

Machine Learning · Computer Science 2026-02-23 Benjamin Honoré , Alba Carballo-Castro , Yiming Qin , Pascal Frossard

Equivariant machine learning is an approach for designing deep learning models that respect the symmetries of the problem, with the aim of reducing model complexity and improving generalization. In this paper, we focus on an extension of…

Machine Learning · Computer Science 2024-12-10 Ya-Wei Eileen Lin , Ronen Talmon , Ron Levie

The rising adoption of machine learning in high energy physics and lattice field theory necessitates the re-evaluation of common methods that are widely used in computer vision, which, when applied to problems in physics, can lead to…

High Energy Physics - Lattice · Physics 2021-10-12 Srinath Bulusu , Matteo Favoni , Andreas Ipp , David I. Müller , Daniel Schuh

Molecular interactions often involve high-order relationships that cannot be fully captured by traditional graph-based models limited to pairwise connections. Hypergraphs naturally extend graphs by enabling multi-way interactions, making…

Machine Learning · Computer Science 2025-05-12 Tien Dang , Truong-Son Hy

Graph machine learning architectures are typically tailored to specific tasks on specific datasets, which hinders their broader applicability. This has led to a new quest in graph machine learning: how to build graph foundation models…

Machine Learning · Computer Science 2025-10-29 Ben Finkelshtein , İsmail İlkan Ceylan , Michael Bronstein , Ron Levie

Permutation equivariant neural networks are typically used to learn from data that lives on a graph. However, for any graph $G$ that has $n$ vertices, using the symmetric group $S_n$ as its group of symmetries does not take into account the…

Machine Learning · Computer Science 2024-05-29 Edward Pearce-Crump , William J. Knottenbelt

In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures…

Machine Learning · Computer Science 2022-04-28 Anwesh Bhattacharya , Marios Mattheakis , Pavlos Protopapas

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

Recent advances in Graph Neural Networks (GNNs) have explored the potential of random noise as an input feature to enhance expressivity across diverse tasks. However, naively incorporating noise can degrade performance, while architectures…

Machine Learning · Computer Science 2025-02-05 Xiyuan Wang , Muhan Zhang

Symmetries (transformations by group actions) are present in many datasets, and leveraging them holds considerable promise for improving predictions in machine learning. In this work, we aim to understand when and how deep networks -- with…

Machine Learning · Computer Science 2025-06-27 Andrea Perin , Stephane Deny

Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph. One aspect that is often overlooked is whether the graph…

Machine Learning · Computer Science 2020-01-31 Zekarias T. Kefato , Nasrullah Sheikh , Alberto Montresor

Conformal symmetries, i.e.\ coordinate transformations that preserve angles, play a key role in many fields, including physics, mathematics, computer vision and (geometric) machine learning. Here we build a neural network that is…

Machine Learning · Computer Science 2025-05-20 Maksim Zhdanov , Nabil Iqbal , Erik Bekkers , Patrick Forré