标题： 我们是否需要等变模型来进行分子生成？ 显示英文标题

标题： Do we need equivariant models for molecule generation?

摘要： 深度生成模型在分子发现中的应用日益广泛，大多数最近的方法依赖于等变图神经网络（GNNs），假设显式等变性对于生成高质量的3D分子是必不可少的。 然而，这些模型复杂，难以训练，并且扩展性差。 我们研究了是否可以使用带有旋转增强的非等变卷积神经网络（CNNs）来学习等变性并达到等变模型的性能。 我们推导了一个损失分解，将预测误差与等变误差分开，并评估模型大小、数据集大小和训练时长如何影响去噪、分子生成和属性预测的性能。 据我们所知，这是首次在生成任务中分析学习到的等变性的研究。 显示英文摘要

摘要： Deep generative models are increasingly used for molecular discovery, with most recent approaches relying on equivariant graph neural networks (GNNs) under the assumption that explicit equivariance is essential for generating high-quality 3D molecules. However, these models are complex, difficult to train, and scale poorly. We investigate whether non-equivariant convolutional neural networks (CNNs) trained with rotation augmentations can learn equivariance and match the performance of equivariant models. We derive a loss decomposition that separates prediction error from equivariance error, and evaluate how model size, dataset size, and training duration affect performance across denoising, molecule generation, and property prediction. To our knowledge, this is the first study to analyze learned equivariance in generative tasks.