提出新型图生成模型GraViti，实现更优的分子图重建与生成。
GraViti: Graph-Level Variational Autoencoders with Relaxed Permutation Invariance
- 基于Transformer设计图级变分自编码器，直接学习全局图表示
- 在分子数据集上实现顶尖重建精度，且生成结构符合化学规则
- 打破节点排列不变性限制，适合有标准节点顺序的领域
我们提出GraViti，一种基于Transformer的图级变分自编码器，可将完整图映射为紧凑的潜在向量。该设计构建了真正的图级潜在空间，支持平滑插值、属性引导搜索等下游任务，突破了节点级嵌入的局限。在分子基准测试中，GraViti能解码出符合训练数据中化学约束的有效样本，表明模型可直接从图级表示中恢复领域规则。我们还发现，在存在可靠规范节点排序的领域（如分子或贝叶斯网络），强制排列不变性反而会损害一致重构。GraViti在大规模数据集上达到当前最优重建准确率，具备出色的生成性能。其单步解码机制提供轻量替代方案，相比复杂生成流程仍保持良好样本质量。
原文摘要 · Abstract (English)
We introduce GraViti, a transformer-based graph-level variational autoencoder that maps entire graphs to compact latent vectors. This design produces a true graph-level latent space that supports smooth interpolation, property-guided search, and other downstream tasks beyond the constraints of node-level embeddings. On molecular benchmarks, GraViti learns to decode valid samples that follow the chemical constraints present in the training data, showing that the model recovers domain rules directly from graph-level representations. We also show that, in domains where a reliable canonical node ordering exists such as molecules or bayesian networks, enforcing permutation invariance can prove detrimental for consistent reconstruction. GraViti achieves state-of-the-art reconstruction accuracy on large datasets, and provides solid generative performance. Its single-step decoding offers a lightweight alternative to more complex generation pipelines while maintaining practical sample quality.
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。