中文
相关论文

相关论文: Multivector Neurons: Better and Faster O(n)-Equiva…

200 篇论文

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…

机器学习 · 计算机科学 2025-03-14 Viet-Hoang Tran , Thieu N. Vo , Tho Tran Huu , Tan Minh Nguyen

We introduce Clifford Group Equivariant Neural Networks: a novel approach for constructing $\mathrm{O}(n)$- and $\mathrm{E}(n)$-equivariant models. We identify and study the $\textit{Clifford group}$, a subgroup inside the Clifford algebra…

机器学习 · 计算机科学 2023-10-24 David Ruhe , Johannes Brandstetter , Patrick Forré

We introduce Clifford Group Equivariant Simplicial Message Passing Networks, a method for steerable E(n)-equivariant message passing on simplicial complexes. Our method integrates the expressivity of Clifford group-equivariant layers with…

人工智能 · 计算机科学 2024-03-13 Cong Liu , David Ruhe , Floor Eijkelboom , Patrick Forré

Clifford Group Equivariant Neural Networks (CGENNs) leverage Clifford algebras and multivectors as an alternative approach to incorporating group equivariance to ensure symmetry constraints in neural representations. In principle, this…

机器学习 · 计算机科学 2025-06-11 Riccardo Ali , Paulina Kulytė , Haitz Sáez de Ocáriz Borde , Pietro Liò

Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and…

机器学习 · 计算机科学 2022-03-15 Wenbing Huang , Jiaqi Han , Yu Rong , Tingyang Xu , Fuchun Sun , Junzhou Huang

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, for instance,…

机器学习 · 计算机科学 2024-07-09 Maksim Zhdanov , David Ruhe , Maurice Weiler , Ana Lucic , Johannes Brandstetter , Patrick Forré

Many scientific problems require to process data in the form of geometric graphs. Unlike generic graph data, geometric graphs exhibit symmetries of translations, rotations, and/or reflections. Researchers have leveraged such inductive bias…

机器学习 · 计算机科学 2022-02-23 Jiaqi Han , Yu Rong , Tingyang Xu , Wenbing Huang

Learning and reasoning about 3D molecular structures with varying size is an emerging and important challenge in machine learning and especially in drug discovery. Equivariant Graph Neural Networks (GNNs) can simultaneously leverage the…

机器学习 · 计算机科学 2022-03-03 Tuan Le , Frank Noé , Djork-Arné Clevert

Many problems in computer vision and machine learning can be cast as learning on hypergraphs that represent higher-order relations. Recent approaches for hypergraph learning extend graph neural networks based on message passing, which is…

机器学习 · 计算机科学 2022-08-23 Jinwoo Kim , Saeyoon Oh , Sungjun Cho , Seunghoon Hong

Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. However, they still encounter several challenges: 1) Physical laws abide by symmetry, which is a vital inductive bias accounting for model…

机器学习 · 计算机科学 2022-10-14 Jiaqi Han , Wenbing Huang , Hengbo Ma , Jiachen Li , Joshua B. Tenenbaum , Chuang Gan

Equivariant Graph Neural Networks (GNNs) have achieved remarkable success across diverse scientific applications. However, existing approaches face critical efficiency challenges when scaling to large geometric graphs and suffer significant…

机器学习 · 计算机科学 2025-06-25 Yuelin Zhang , Jiacheng Cen , Jiaqi Han , Wenbing Huang

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does…

机器学习 · 计算机科学 2022-02-17 Victor Garcia Satorras , Emiel Hoogeboom , Max Welling

Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide…

机器学习 · 计算机科学 2021-07-14 Bowen Jing , Stephan Eismann , Pratham N. Soni , Ron O. Dror

Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these…

机器学习 · 计算机科学 2023-04-12 Weitao Du , Yuanqi Du , Limei Wang , Dieqiao Feng , Guifeng Wang , Shuiwang Ji , Carla Gomes , Zhi-Ming Ma

Equivariant Graph Neural Networks (GNNs) have demonstrated significant success across various applications. To achieve completeness -- that is, the universal approximation property over the space of equivariant functions -- the network must…

机器学习 · 计算机科学 2025-10-16 Jiacheng Cen , Anyi Li , Ning Lin , Tingyang Xu , Yu Rong , Deli Zhao , Zihe Wang , Wenbing Huang

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 generalise equivariant…

机器学习 · 计算机科学 2022-03-29 Johannes Brandstetter , Rob Hesselink , Elise van der Pol , Erik J Bekkers , Max Welling

We propose, implement, and compare with competitors a new architecture of equivariant neural networks based on geometric (Clifford) algebras: Generalized Lipschitz Group Equivariant Neural Networks (GLGENN). These networks are equivariant…

机器学习 · 计算机科学 2025-12-04 Ekaterina Filimoshina , Dmitry Shirokov

Graph Neural Networks (GNNs) are key tools for graph representation learning, demonstrating strong results across diverse prediction tasks. In this paper, we present Convexified Message-Passing Graph Neural Networks (CGNNs), a novel and…

机器学习 · 计算机科学 2026-01-27 Saar Cohen , Noa Agmon , Uri Shaham

The principle of equivariance to symmetry transformations enables a theoretically grounded approach to neural network architecture design. Equivariant networks have shown excellent performance and data efficiency on vision and medical…

机器学习 · 计算机科学 2019-05-15 Taco S. Cohen , Maurice Weiler , Berkay Kicanaoglu , Max Welling

Triangular meshes are widely used to represent three-dimensional objects. As a result, many recent works have address the need for geometric deep learning on 3D mesh. However, we observe that the complexities in many of these architectures…

机器学习 · 计算机科学 2024-02-20 Thuan Trang , Nhat Khang Ngo , Daniel Levy , Thieu N. Vo , Siamak Ravanbakhsh , Truong Son Hy
‹ 上一页 1 2 3 10 下一页 ›