English
Related papers

Related papers: Using Multiple Vector Channels Improves E(n)-Equiv…

200 papers

We present a SE(3)-equivariant graph neural network (GNN) approach that directly predicting the formation factor and effective permeability from micro-CT images. FFT solvers are established to compute both the formation factor and effective…

The introduction of relevant physical information into neural network architectures has become a widely used and successful strategy for improving their performance. In lattice gauge theories, such information can be identified with gauge…

High Energy Physics - Lattice · Physics 2023-01-11 Matteo Favoni , Andreas Ipp , David I. Müller

Graph neural networks (GNNs) have been applied to a large variety of applications in materials science and chemistry. Here, we recapitulate the graph construction for crystalline (periodic) materials and investigate its impact on the GNNs…

Machine Learning · Computer Science 2023-08-10 Robin Ruff , Patrick Reiser , Jan Stühmer , Pascal Friederich

Graph Neural Networks (GNN) come in many flavors, but should always be either invariant (permutation of the nodes of the input graph does not affect the output) or equivariant (permutation of the input permutes the output). In this paper,…

Machine Learning · Computer Science 2019-10-25 Nicolas Keriven , Gabriel Peyré

Optical spectroscopies provide a powerful tool for harnessing light-matter interactions for unraveling complex electronic features such as the flat bands and nontrivial topologies of materials. These insights are crucial for the development…

Materials Science · Physics 2025-12-11 Ting-Wei Hsu , Zhenyao Fang , Arun Bansil , Qimin Yan

This paper presents $\mathrm{E}(n)$ Equivariant Message Passing Simplicial Networks (EMPSNs), a novel approach to learning on geometric graphs and point clouds that is equivariant to rotations, translations, and reflections. EMPSNs can…

Machine Learning · Computer Science 2023-10-24 Floor Eijkelboom , Rob Hesselink , Erik Bekkers

Message-passing neural networks (MPNN) have shown extremely high efficiency and accuracy in predicting the physical properties of molecules and crystals, and are expected to become the next-generation material simulation tool after the…

Materials Science · Physics 2022-01-19 Yang Zhong , Hongyu Yu , Xingao Gong , Hongjun Xiang

Graph neural networks (GNNs) have demonstrated success in modeling relational data, especially for data that exhibits homophily: when a connection between nodes tends to imply that they belong to the same class. However, while this…

Machine Learning · Computer Science 2023-06-23 Andreea Deac , Jian Tang

Graph neural networks (GNNs) are commonly described as being permutation equivariant with respect to node relabeling in the graph. This symmetry of GNNs is often compared to the translation equivariance of Euclidean convolution neural…

Machine Learning · Statistics 2023-11-20 Ningyuan Huang , Ron Levie , Soledad Villar

We introduce a novel architecture for graph networks which is equivariant to any transformation in the coordinate embeddings that preserves the distance between neighbouring nodes. In particular, it is equivariant to the Euclidean and…

Machine Learning · Computer Science 2021-07-13 Francesco Farina , Emma Slade

Equivariant Graph Neural Networks (GNNs) that incorporate E(3) symmetry have achieved significant success in various scientific applications. As one of the most successful models, EGNN leverages a simple scalarization technique to perform…

Machine Learning · Computer Science 2025-10-16 Jiacheng Cen , Anyi Li , Ning Lin , Yuxiang Ren , Zihe Wang , Wenbing Huang

The identification of cancer genes is a critical yet challenging problem in cancer genomics research. Existing computational methods, including deep graph neural networks, fail to exploit the multilayered gene-gene interactions or provide…

Machine Learning · Computer Science 2023-05-04 Michail Chatzianastasis , Michalis Vazirgiannis , Zijun Zhang

We introduce an $E(n)$-equivariant Transformer architecture for spatio-temporal graph data. By imposing rotation, translation, and permutation equivariance inductive biases in both space and time, we show that the Spacetime…

Machine Learning · Computer Science 2024-08-13 Sergio G. Charles

This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes…

Artificial Intelligence · Computer Science 2020-10-22 Douglas De Rizzo Meneghetti , Reinaldo Augusto da Costa Bianchi

Graph neural networks (GNNs) have gained traction in high-energy physics (HEP) for their potential to improve accuracy and scalability. However, their resource-intensive nature and complex operations have motivated the development of…

Instrumentation and Detectors · Physics 2023-04-12 Daniel Murnane , Savannah Thais , Ameya Thete

Equivariant network architectures are a well-established tool for predicting invariant or equivariant quantities. However, almost all learning problems considered in this context feature a global symmetry, i.e. each point of the underlying…

Machine Learning · Computer Science 2025-02-24 Longde Huang , Oleksandr Balabanov , Hampus Linander , Mats Granath , Daniel Persson , Jan E. Gerken

We formulate an XAI-based model improvement approach for Graph Neural Networks (GNNs) for node classification, called Explanation Enhanced Graph Learning (EEGL). The goal is to improve predictive performance of GNN using explanations. EEGL…

Machine Learning · Computer Science 2024-03-13 Harish G. Naik , Jan Polster , Raj Shekhar , Tamás Horváth , György Turán

Designing neural network architectures that can handle data symmetry is crucial. This is especially important for geometric graphs whose properties are equivariance under Euclidean transformations. Current equivariant graph neural networks…

Machine Learning · Computer Science 2025-03-14 Viet-Hoang Tran , Thieu N. Vo , Tho Tran Huu , Tan Minh Nguyen

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

Driven by the outstanding performance of neural networks in the structured Euclidean domain, recent years have seen a surge of interest in developing neural networks for graphs and data supported on graphs. The graph is leveraged at each…

Machine Learning · Computer Science 2021-07-28 Elvin Isufi , Fernando Gama , Alejandro Ribeiro