GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
This work addresses a bottleneck in neural architecture analysis for researchers and engineers, offering a novel method that balances accuracy and efficiency, though it is incremental in improving upon existing approaches.
The paper tackles the problem of discovering frequent subgraph patterns in neural architectures, where existing methods are either accurate but computationally prohibitive or tractable but ineffective. The proposed GraDE framework achieves up to 114% improvement in ranking accuracy and up to 30x higher median frequency compared to sampling-based baselines.
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.