# GraphCrop: Subgraph Cropping for Graph Classification

arXiv: https://arxiv.org/abs/2009.10564 · HTML: https://mlsanity.com/paper/2009.10564/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 30 of 31)

- [G-Mixup: Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2202.07179/) (2022)
- [Size-Invariant Graph Representations for Graph Classification Extrapolations](https://mlsanity.com/paper/2103.05045/) (2021)
- [Graph Rationalization with Environment-based Augmentations](https://mlsanity.com/paper/2206.02886/) (2022)
- [Graph Data Augmentation for Graph Machine Learning: A Survey](https://mlsanity.com/paper/2202.08871/) (2022)
- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [Model-Agnostic Augmentation for Accurate Graph Classification](https://mlsanity.com/paper/2202.10107/) (2022)
- [Automated Data Augmentations for Graph Classification](https://mlsanity.com/paper/2202.13248/) (2022)
- [Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications](https://mlsanity.com/paper/2306.15963/) (2023)
- [Data Augmentation on Graphs: A Technical Survey](https://mlsanity.com/paper/2212.09970/) (2022)
- [Graph Augmentation Learning](https://mlsanity.com/paper/2203.09020/) (2022)
- [Spectral Augmentations for Graph Contrastive Learning](https://mlsanity.com/paper/2302.02909/) (2023)
- [ifMixup: Interpolating Graph Pair to Regularize Graph Classification](https://mlsanity.com/paper/2110.09344/) (2021)
- [Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networks](https://mlsanity.com/paper/2406.05482/) (2024)
- [Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media](https://mlsanity.com/paper/2403.00037/) (2024)
- [Metric Based Few-Shot Graph Classification](https://mlsanity.com/paper/2206.03695/) (2022)
- [GNN-Ensemble: Towards Random Decision Graph Neural Networks](https://mlsanity.com/paper/2303.11376/) (2023)
- [Towards Efficient Training of Graph Neural Networks: A Multiscale Approach](https://mlsanity.com/paper/2503.19666/) (2025)
- [EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost](https://mlsanity.com/paper/2306.01310/) (2023)
- [DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks](https://mlsanity.com/paper/2409.19620/) (2024)
- [SoftEdge: Regularizing Graph Classification with Random Soft Edges](https://mlsanity.com/paper/2204.10390/) (2022)
- [Demystifying Bitcoin Address Behavior via Graph Neural Networks](https://mlsanity.com/paper/2211.14582/) (2022)
- [Latent Conditional Diffusion-based Data Augmentation for Continuous-Time Dynamic Graph Model](https://mlsanity.com/paper/2407.08500/) (2024)
- [Data Augmentation for Graph Data: Recent Advancements](https://mlsanity.com/paper/2208.11973/) (2022)
- [Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs](https://mlsanity.com/paper/2406.16552/) (2024)
- [Graph Neural Networks for Jamming Source Localization](https://mlsanity.com/paper/2506.03196/) (2025)
- [Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentation](https://mlsanity.com/paper/2304.05749/) (2023)
- [Subgraph Networks Based Contrastive Learning](https://mlsanity.com/paper/2306.03506/) (2023)
- [GDM: Dual Mixup for Graph Classification with Limited Supervision](https://mlsanity.com/paper/2309.10134/) (2023)
- [SGA: A Graph Augmentation Method for Signed Graph Neural Networks](https://mlsanity.com/paper/2310.09705/) (2023)
- [Heterogenous Memory Augmented Neural Networks](https://mlsanity.com/paper/2310.10909/) (2023)

## Abstract (arXiv)

We present a new method to regularize graph neural networks (GNNs) for better generalization in graph classification. Observing that the omission of sub-structures does not necessarily change the class label of the whole graph, we develop the GraphCrop (Subgraph Cropping) data augmentation method to simulate the real-world noise of sub-structure omission. In principle, GraphCrop utilizes a node-centric strategy to crop a contiguous subgraph from the original graph while maintaining its connectivity. By preserving the valid structure contexts for graph classification, we encourage GNNs to understand the content of graph structures in a global sense, rather than rely on a few key nodes or edges, which may not always be present. GraphCrop is parameter learning free and easy to implement within existing GNN-based graph classifiers. Qualitatively, GraphCrop expands the existing training set by generating novel and informative augmented graphs, which retain the original graph labels in most cases. Quantitatively, GraphCrop yields significant and consistent gains on multiple standard datasets, and thus enhances the popular GNNs to outperform the baseline methods.