提升分子图生成的精度，关键在精确的图匹配机制。
Auto-encoding Molecules: Graph-Matching Capabilities Matter
- 用基于Transformer的图解码器替代传统GNN，增强全局注意力表达能力。
- 图匹配精度显著影响训练稳定性和新分子结构生成效果。
- 适合从事分子生成、图神经网络优化的研究者参考。
自编码器是有效的深度学习模型，可作为生成模型并学习用于下游任务的潜在表示。图自编码器（以消息传递网络实现编码器和解码器）因其能生成排列不变的图表示而引人注目。然而，该方法面临挑战：从单个向量解码图结构困难，且输入与输出图之间的比较需要有效的排列不变相似性度量。因此，许多研究依赖近似方法。本文探讨了图匹配精度对变分自编码器（VAE）训练行为和生成能力的影响。贡献有二：(1) 提出一种基于Transformer的消息传递图解码器，相比传统GNN更具鲁棒性和表达力，得益于全局注意力机制；(2) 证明图匹配精度对训练行为具有显著影响，且对有效的新分子图生成至关重要。代码已公开于https://github.com/mcunow/graph-matching。
原文摘要 · Abstract (English)
Autoencoders are effective deep learning models that can function as generative models and learn latent representations for downstream tasks. The use of graph autoencoders - with both encoder and decoder implemented as message passing networks - is intriguing due to their ability to generate permutation-invariant graph representations. However, this approach faces difficulties because decoding a graph structure from a single vector is challenging, and comparing input and output graphs requires an effective permutation-invariant similarity measure. As a result, many studies rely on approximate methods. In this work, we explore the effect of graph matching precision on the training behavior and generation capabilities of a Variational Autoencoder (VAE). Our contribution is two-fold: (1) we propose a transformer-based message passing graph decoder as an alternative to a graph neural network decoder, that is more robust and expressive by leveraging global attention mechanisms. (2) We show that the precision of graph matching has significant impact on training behavior and is essential for effective de novo (molecular) graph generation. Code is available at https://github.com/mcunow/graph-matching
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。