# Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation

arXiv: https://arxiv.org/abs/2111.05639 · HTML: https://mlsanity.com/paper/2111.05639/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 10 Nov 2021.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View](https://mlsanity.com/paper/1909.03211/) (2019)
- [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://mlsanity.com/paper/1704.02901/) (2017)
- [Adversarial Attack on Graph Structured Data](https://mlsanity.com/paper/1806.02371/) (2018)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [A Fair Comparison of Graph Neural Networks for Graph Classification](https://mlsanity.com/paper/1912.09893/) (2019)
- [Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2006.06830/) (2020)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Co-Mixup: Saliency Guided Joint Mixup with Supermodular Diversity](https://mlsanity.com/paper/2102.03065/) (2021)
- [Augmenting Data with Mixup for Sentence Classification: An Empirical Study](https://mlsanity.com/paper/1905.08941/) (2019)

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

- [G-Mixup: Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2202.07179/) (2022)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (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)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Automated Data Augmentations for Graph Classification](https://mlsanity.com/paper/2202.13248/) (2022)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [Graph Invariant Learning with Subgraph Co-mixup for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2312.10988/) (2023)
- [Graph Mixup with Soft Alignments](https://mlsanity.com/paper/2306.06788/) (2023)
- [Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications](https://mlsanity.com/paper/2306.15963/) (2023)
- [GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering](https://mlsanity.com/paper/2210.15721/) (2022)
- [NodeMixup: Tackling Under-Reaching for Graph Neural Networks](https://mlsanity.com/paper/2312.13032/) (2023)
- [Data Augmentation on Graphs: A Technical Survey](https://mlsanity.com/paper/2212.09970/) (2022)
- [Graph Structure and Feature Extrapolation for Out-of-Distribution Generalization](https://mlsanity.com/paper/2306.08076/) (2023)
- [A Graph is Worth K Words: Euclideanizing Graph using Pure Transformer](https://mlsanity.com/paper/2402.02464/) (2024)
- [Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs](https://mlsanity.com/paper/2502.13555/) (2025)
- [Metric Based Few-Shot Graph Classification](https://mlsanity.com/paper/2206.03695/) (2022)
- [IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors](https://mlsanity.com/paper/2405.00957/) (2024)
- [EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost](https://mlsanity.com/paper/2306.01310/) (2023)
- [Mixed Supervised Graph Contrastive Learning for Recommendation](https://mlsanity.com/paper/2404.15954/) (2024)
- [SoftEdge: Regularizing Graph Classification with Random Soft Edges](https://mlsanity.com/paper/2204.10390/) (2022)
- [Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2401.09953/) (2024)
- [Harnessing Collective Structure Knowledge in Data Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2405.10633/) (2024)
- [AugWard: Augmentation-Aware Representation Learning for Accurate Graph Classification](https://mlsanity.com/paper/2503.21105/) (2025)
- [Data Augmentation for Graph Data: Recent Advancements](https://mlsanity.com/paper/2208.11973/) (2022)
- [S-Mixup: Structural Mixup for Graph Neural Networks](https://mlsanity.com/paper/2308.08097/) (2023)
- [GIMM: InfoMin-Max for Automated Graph Contrastive Learning](https://mlsanity.com/paper/2305.17437/) (2023)
- [GDM: Dual Mixup for Graph Classification with Limited Supervision](https://mlsanity.com/paper/2309.10134/) (2023)
- [Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study](https://mlsanity.com/paper/2311.12737/) (2023)

## Abstract (arXiv)

Graph-structured datasets usually have irregular graph sizes and connectivities, rendering the use of recent data augmentation techniques, such as Mixup, difficult. To tackle this challenge, we present the first Mixup-like graph augmentation method at the graph-level called Graph Transplant, which mixes irregular graphs in data space. To be well defined on various scales of the graph, our method identifies the sub-structure as a mix unit that can preserve the local information. Since the mixup-based methods without special consideration of the context are prone to generate noisy samples, our method explicitly employs the node saliency information to select meaningful subgraphs and adaptively determine the labels. We extensively validate our method with diverse GNN architectures on multiple graph classification benchmark datasets from a wide range of graph domains of different sizes. Experimental results show the consistent superiority of our method over other basic data augmentation baselines. We also demonstrate that Graph Transplant enhances the performance in terms of robustness and model calibration.