用局部消息传递实现高效图生成，无需全局注意力。
Local Message-Passing for Discrete Graph Generation
- 提出GenGNN，通过耦合节点边状态进行局部消息传递。
- 在标准数据集上有效性超90%，推理速度提升2至5倍。
- 适合追求高效图生成且无需复杂架构的研究者。
离散图生成已成为建模图结构数据的强大范式，但现有先进模型常依赖图Transformer或高阶架构。本文重新审视这一设计假设，提出GenGNN——一种用于图生成的模块化消息传递主干网络。GenGNN通过保持边场并持续精炼耦合的节点-边图状态，在不使用全局注意力的情况下实现强大生成能力。集成GenGNN的扩散模型在标准基准数据集上有效性超过90%，性能接近图Transformer主干，且推理速度提升达2倍甚至5倍。系统性消融实验表明，GenGNN在生成去噪过程中对过平滑具有鲁棒性，每个组件对下游生成质量均不可或缺。表示空间分析显示，即使在深层，GenGNN也学习到与更理论表达力强的架构功能相似的表示。因此，GenGNN将局部消息传递提升至挑战当前认为高性能离散图生成需全局注意力或高阶表示的主流观点。
原文摘要 · Abstract (English)
Discrete graph generation has emerged as a powerful paradigm for modeling graph-structured data, yet state of the art models often rely on Graph Transformers or higher order architectures. We revisit this design assumption by introducing GenGNN, a modular message passing backbone for graph generation. GenGNN enables powerful generation by persisting edge fields through latent refinement of coupled node edge graph states, all without requiring global attention. Diffusion models integrating GenGNN achieve over 90 percent validity on standard benchmark datasets, performing within margins of Graph Transformer backbones and achieving up to 2x or even 5x faster inference. Systematic ablations isolate how GenGNN is resilient to oversmoothing during generative denoising, indicating each GenGNN component is necessary for downstream generation quality. Finally, representation-space analysis suggests GenGNN learns functionally similar representations to more theoretically-expressive architectures; even at deeper layers. As such, GenGNN uplifts local message-passing to challenge prevailing assumptions that performant discrete graph generation requires global attention or higher-order representations. Source Code Available Here
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。