GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures

TL;DR

GraDE introduces a graph diffusion estimator that significantly improves the discovery of frequent subgraph patterns in neural architectures, balancing computational efficiency with high discovery accuracy.

Contribution

The paper presents GraDE, the first graph diffusion model for identifying frequent subgraphs, enabling scalable and accurate pattern discovery in neural network analysis.

Findings

Achieves up to 114% better ranking accuracy than sampling methods.

Discoveries of large-scale frequent patterns with up to 30x higher median frequency.

Demonstrates superior performance in identifying network motifs.

Abstract

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.