通过动态调度实现图结构生成的精细控制。
Fine-Grained Graph Generation through Latent Mixture Scheduling
- 设计混合调度器，融合图与属性先验，优化潜在空间。
- 在五个真实数据集上，生成质量与可控性均优于基线。
- 适合需要精确控制图结构的应用场景如药物发现。
结构感知的图生成旨在生成满足特定拓扑属性的图，在药物发现、社交网络建模和知识图谱构建等领域有重要应用。现有方法仅能粗粒度控制图属性，本文提出一种新型条件变分自编码器，实现图生成的细粒度结构控制。该方法通过动态对齐图驱动与属性驱动的表示，优化解码器的潜在空间，提升图保真度与控制满足度。具体而言，引入混合调度器，逐步整合图与控制先验。在五个真实世界数据集上的实验表明，所提模型在生成质量与可控性方面均显著优于近期基线方法。
原文摘要 · Abstract (English)
Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling, and knowledge graph construction. Unlike existing methods that only provide coarse control over graph properties, we introduce a novel conditional variational autoencoder for fine-grained structural control in graph generation. The approach refines the decoder's latent space by dynamically aligning graph- and property-driven representations to improve both graph fidelity and control satisfaction. Specifically, the approach implements a mixture scheduler that progressively integrates graph and control priors. Experiments on five real-world datasets show the efficacy of the proposed model compared to recent baselines, achieving high generation quality while maintaining high controllability.
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。