用图扩散模型高效发现神经网络中的高频子图模式
GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
- 引入图扩散模型评分子图典型性，替代传统枚举或采样
- 排名准确率提升最高达114%，发现的子图频率高出30倍
- 适合研究神经架构设计、结构优化与自动化搜索的人看
在神经网络架构中发现频繁出现的子图模式或网络基元，对于提升效率、加速设计和揭示结构规律至关重要。然而，随着子图规模增大，基于枚举的方法虽精确但计算成本过高，而基于采样的方法虽可计算可行，却显著降低发现能力。为此，本文提出GraDE——一种基于扩散引导的搜索框架，其核心是首个将图扩散模型用于识别频繁子图的图扩散估计器（GraDE），通过学习分布内子图的典型性得分实现高效发现。大量实验表明，该估计器在排名准确率上相较采样基线最高提升114%；得益于此，所提框架成功发现大规模频繁模式，其平均频率较采样方法最高提升30倍。
原文摘要 · Abstract (English)
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.
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。