paper-with-me

홈 › Papers

Geometric Algebra Transformer

2023-05-28 · NeurIPS 2023 11 · Johann Brehmer, Pim de Haan, Sönke Behrends, Taco Cohen

Problems involving geometric data arise in physics, chemistry, robotics, computer vision, and many other fields. Such data can take numerous forms, for instance points, direction vectors, translations, or rotations, but to date there is no single architecture that can be applied to such a wide variety of geometric types while respecting their symmetries. In this paper we introduce the Geometric Algebra Transformer (GATr), a general-purpose architecture for geometric data. GATr represents inputs, outputs, and hidden states in the projective geometric (or Clifford) algebra, which offers an efficient 16-dimensional vector-space representation of common geometric objects as well as operators acting on them. GATr is equivariant with respect to E(3), the symmetry group of 3D Euclidean space. As a Transformer, GATr is versatile, efficient, and scalable. We demonstrate GATr in problems from n-body modeling to wall-shear-stress estimation on large arterial meshes to robotic motion planning. GATr consistently outperforms both non-geometric and equivariant baselines in terms of error, data efficiency, and scalability.

📄 PDF Abstract BibTeX arXiv:2305.18415

Code (2)

qualcomm-ai-research/geometric-algebra-transformer 공식 구현 pytorch
heidelberg-hepml/lorentz-gatr pytorch

Tasks

Motion Planning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers

2023-11-08 · Pim de Haan, Taco Cohen, Johann Brehmer

The Geometric Algebra Transformer (GATr) is a versatile architecture for geometric deep learning based on projective geometric algebra. We generalize this architecture into a blueprint that allows one to construct a scal…

Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics

2024-05-23 · Jonas Spinner, Victor Bresó, Pim de Haan, Tilman Plehn 외

Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr)…

A Lorentz-Equivariant Transformer for All of the LHC

2024-11-01 · Johann Brehmer, Víctor Bresó, Pim de Haan, Tilman Plehn 외

We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometr…

All

Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning

2025-07-08 · Xiatao Sun, Yuxuan Wang, Shuo Yang, Yinxing Chen 외 arxiv

Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient. A key reason is that networks must relearn fundamental spatial concepts, such as translations and rotations, from sc…

Robot Manipulation

Toward a Functional Geometric Algebra for Natural Language Semantics

2026-04-28 · James Pustejovsky arxiv

Distributional and neural approaches to natural language semantics have been built almost exclusively on conventional linear algebra: vectors, matrices, tensors, and the operations that accompany them. These methods have…