将张量场网络转为局部规范表示，提速并保持几何不变性。
Equivariance by Local Canonicalization: A Matter of Representation
- 用局部规范化替代复杂张量运算，提升效率
- 新方法在分子数据上运行速度提升4倍以上
- 适合想快速加几何不变性的图神经网络开发者
等变神经网络对分子和几何数据学习具有强归纳偏置，但常依赖专用且计算昂贵的张量操作。我们提出一个框架，将现有张量场网络迁移至更高效的局部规范化范式，在保持等变性的同时显著提升运行速度。该框架系统比较了不同等变表示的理论复杂度、实际运行时间和预测精度。我们发布了tensor_frames工具包，基于PyTorchGeometric，可轻松将等变性集成到任意标准消息传递神经网络中。
原文摘要 · Abstract (English)
Equivariant neural networks offer strong inductive biases for learning from molecular and geometric data but often rely on specialized, computationally expensive tensor operations. We present a framework to transfers existing tensor field networks into the more efficient local canonicalization paradigm, preserving equivariance while significantly improving the runtime. Within this framework, we systematically compare different equivariant representations in terms of theoretical complexity, empirical runtime, and predictive accuracy. We publish the tensor_frames package, a PyTorchGeometric based implementation for local canonicalization, that enables straightforward integration of equivariance into any standard message passing neural network.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。