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

arXiv: https://arxiv.org/abs/2602.03257 · HTML: https://mlsanity.com/paper/2602.03257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [DiGress: Discrete Denoising diffusion for graph generation](https://mlsanity.com/paper/2209.14734/) (2022)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [MolGAN: An implicit generative model for small molecular graphs](https://mlsanity.com/paper/1805.11973/) (2018)
- [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://mlsanity.com/paper/1902.09635/) (2019)
- [Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design](https://mlsanity.com/paper/2402.04997/) (2024)
- [Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations](https://mlsanity.com/paper/2202.02514/) (2022)
- [Permutation Invariant Graph Generation via Score-Based Generative Modeling](https://mlsanity.com/paper/2003.00638/) (2020)
- [Learning Gradient Fields for Molecular Conformation Generation](https://mlsanity.com/paper/2105.03902/) (2021)
- [NetGAN: Generating Graphs via Random Walks](https://mlsanity.com/paper/1803.00816/) (2018)
- [Graph Normalizing Flows](https://mlsanity.com/paper/1905.13177/) (2019)
- [DeFoG: Discrete Flow Matching for Graph Generation](https://mlsanity.com/paper/2410.04263/) (2024)
- [Generative Diffusion Models on Graphs: Methods and Applications](https://mlsanity.com/paper/2302.02591/) (2023)
- [Discrete-state Continuous-time Diffusion for Graph Generation](https://mlsanity.com/paper/2405.11416/) (2024)
- [Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks](https://mlsanity.com/paper/2008.09777/) (2020)
- [NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing](https://mlsanity.com/paper/2006.07116/) (2020)
- [Cometh: A continuous-time discrete-state graph diffusion model](https://mlsanity.com/paper/2406.06449/) (2024)
- [On Redundancy and Diversity in Cell-based Neural Architecture Search](https://mlsanity.com/paper/2203.08887/) (2022)
- [Multi-conditioned Graph Diffusion for Neural Architecture Search](https://mlsanity.com/paper/2403.06020/) (2024)
- [MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation](https://mlsanity.com/paper/2405.12519/) (2024)
- [Representation Learning for Frequent Subgraph Mining](https://mlsanity.com/paper/2402.14367/) (2024)
- [Approximate Network Motif Mining Via Graph Learning](https://mlsanity.com/paper/2206.01008/) (2022)
- [Younger: The First Dataset for Artificial Intelligence-Generated Neural Network Architecture](https://mlsanity.com/paper/2406.15132/) (2024)
- [Studying and Improving Graph Neural Network-based Motif Estimation](https://mlsanity.com/paper/2506.15709/) (2025)

## Abstract (arXiv)

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× higher median frequency than sampling-based methods.