用旋转数据增强的CNN也能生成高质量分子，无需复杂等变模型。
Do we need equivariant models for molecule generation?
- 用旋转增强训练非等变CNN，学习分子3D结构对称性。
- 在分子生成和性质预测任务上，性能接近等变GNN模型。
- 首次分析生成任务中模型对称性的学习机制，适合模型效率研究者。
深度生成模型在分子发现中应用日益广泛，多数近期方法依赖等变图神经网络（GNNs），假设显式等变性对生成高质量3D分子至关重要。然而这些模型结构复杂、难训练且扩展性差。本文探究非等变卷积神经网络（CNNs）在旋转数据增强下能否学习等变性，并匹配等变模型性能。我们推导出损失分解，将预测误差与等变误差分离，评估模型规模、数据集大小和训练时长对去噪、分子生成及性质预测任务的影响。据我们所知，这是首个分析生成任务中学习等变性的研究。
原文摘要 · Abstract (English)
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.
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。