Finding frequently occurring subgraph patterns or network motifs in neural architectures is crucial for optimizing efficiency, accelerating design, and uncovering structural insights. However, as the subgraph size increases, enumeration-based methods are perfectly accurate but computationally prohibitive, while sampling-based methods are computationally tractable but suffer from a severe decline in discovery capability. To address these challenges, this paper proposes GraDE, a diffusion-guided search framework that ensures both computational feasibility and discovery capability. The key innovation is the Graph Diffusion Estimator (GraDE), which is the first to introduce graph diffusion models to identify frequent subgraphs by scoring their typicality within the learned distribution. Comprehensive experiments demonstrate that the estimator achieves superior ranking accuracy, with up to 114\% improvement compared to sampling-based baselines. Benefiting from this, the proposed framework successfully discovers large-scale frequent patterns, achieving up to 30$\times$ higher median frequency than sampling-based methods.

翻译：在神经网络架构中发现频繁出现的子图模式或网络基元对于优化效率、加速设计及揭示结构洞见至关重要。然而，随着子图尺寸增大，基于枚举的方法虽能保证完全精确，但计算成本过高；而基于采样的方法虽计算可行，其发现能力却会急剧下降。为解决这些挑战，本文提出GraDE，一种确保计算可行性与发现能力兼备的扩散引导搜索框架。其核心创新在于图扩散估计器（GraDE），该模型首次引入图扩散方法，通过学习分布中对子图典型性的评分来识别频繁子图。综合实验表明，该估计器实现了卓越的排序准确度，相比基于采样的基线方法提升最高达114%。得益于此，所提框架成功发现了大规模频繁模式，其中位数频率最高可达基于采样方法的30倍。