用潜在空间扩散生成分子图，提升效率并探索最佳实践。
Exploring Molecule Generation Using Latent Space Graph Diffusion
- 在低维潜在空间中通过自编码器进行图扩散，提高生成效率。
- 对比多种扩散方法与网络架构，发现结果对设计选择高度敏感。
- 为分子生成提供可复现的实验基准，适合研究生成模型者参考。
由于分子图的离散特性及多重优化目标，其生成极具挑战性。扩散模型已在多种数据模态中成为最先进方法。对于分子图，基于图神经网络（GNN）的扩散模型已取得显著成果。潜在空间扩散通过自编码器在低维空间中进行扩散，表现出更高的计算效率。然而，针对分子图的潜在空间扩散研究仍较少，且缺乏通用的最佳实践。本文系统探索了不同方法与超参数，对比了生成流模型（去噪扩散、流匹配、热耗散）以及网络架构（GNNs 与 E(3)-等变 GNNs）。实验表明，生成效果对方法选择和设计决策极为敏感。代码已开源：github.com/Prashanth-Pombala/Molecule-Generation-using-Latent-Space-Graph-Diffusion。
原文摘要 · Abstract (English)
Generating molecular graphs is a challenging task due to their discrete nature and the competitive objectives involved. Diffusion models have emerged as SOTA approaches in data generation across various modalities. For molecular graphs, graph neural networks (GNNs) as a diffusion backbone have achieved impressive results. Latent space diffusion, where diffusion occurs in a low-dimensional space via an autoencoder, has demonstrated computational efficiency. However, the literature on latent space diffusion for molecular graphs is scarce, and no commonly accepted best practices exist. In this work, we explore different approaches and hyperparameters, contrasting generative flow models (denoising diffusion, flow matching, heat dissipation) and architectures (GNNs and E(3)-equivariant GNNs). Our experiments reveal a high sensitivity to the choice of approach and design decisions. Code is made available at github.com/Prashanth-Pombala/Molecule-Generation-using-Latent-Space-Graph-Diffusion.
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。