轻量级自回归模型实现高效新颖图生成，突破传统方法扩展性瓶颈。
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
- 基于结构引导的拓扑排序将图转为边序列，接近线性复杂度生成
- 两阶段训练提升新颖性，分子与非分子数据集均实现高有效性和独特性
- 兼容LSTM和Mamba架构，支持超长序列生成，适合大规模图建模任务
生成真实且多样化的图是机器学习中的关键问题，应用于分子发现、电路设计、网络安全等领域。然而，现有图生成模型受限于可扩展性与新颖性：基于扩散的方法需昂贵的全邻接操作和长去噪链，许多自回归与混合模型至少具有二次复杂度，且常仅模仿训练图而非泛化。本文提出一种轻量级自回归框架，利用结构引导的拓扑排序将图序列化为规则边序列，实现近对数线性生成；采用两阶段训练策略，结合探索导向的数据增强与迭代精炼，降低过拟合并促进可控新颖性。在分子与非分子基准上实验表明，该方法在保持高有效性与唯一性的同时显著提升新颖性。框架支持LSTM与Mamba风格因果序列骨干网络，借助大内存加速器可开展超出典型GPU限制的长图序列实验。
原文摘要 · Abstract (English)
Generating realistic and diverse graphs is a key problem in machine learning, with applications in molecular discovery, circuit design, cybersecurity, and beyond. However, current graph generative models remain limited by scalability and novelty. Diffusion-based methods often require costly full-adjacency operations and long denoising chains, while many autoregressive and hybrid models have at least quadratic complexity. In addition, these models often imitate training graphs rather than generalize beyond them. We propose a lightweight autoregressive framework to address these issues. It uses a structure-guided topological ordering to serialize graphs into regular edge sequences, enabling near log-linear generation, and a two-phase training strategy that combines exploration-oriented augmentation with iterative refinement to reduce overfitting and promote controlled novelty. Experiments on molecular and non-molecular benchmarks show that our approach improves novelty while preserving high validity and uniqueness. The framework also supports both LSTM and Mamba-style causal sequence backbones, with large-memory accelerators enabling longer graph-sequence experiments beyond typical GPU limits.
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。