根据数据对称性动态调整采样，降低连续群等变网络计算开销。
Adaptive Sampling for Continuous Group Equivariant Neural Networks
- 按数据对称性自适应调整群采样点数
- 在保持性能的同时减少采样数量和计算量
- 适合需高效处理对称数据的深度学习任务
可旋转网络处理具有内在对称性的数据时，常使用基于傅里叶的非线性，需对整个群进行采样，导致连续群必须离散化。采样点越多，模型性能与等变性越好，但计算成本也越高。为此，我们提出一种自适应采样方法，根据数据中的对称性动态调整采样过程，减少所需群采样点数，降低计算负担。我们探索了多种实现方式及其对模型性能、等变性和计算效率的影响。结果表明，该方法在保持模型性能的同时，实现了边际内存效率提升。
原文摘要 · Abstract (English)
Steerable networks, which process data with intrinsic symmetries, often use Fourier-based nonlinearities that require sampling from the entire group, leading to a need for discretization in continuous groups. As the number of samples increases, both performance and equivariance improve, yet this also leads to higher computational costs. To address this, we introduce an adaptive sampling approach that dynamically adjusts the sampling process to the symmetries in the data, reducing the number of required group samples and lowering the computational demands. We explore various implementations and their effects on model performance, equivariance, and computational efficiency. Our findings demonstrate improved model performance, and a marginal increase in memory efficiency.
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。