Graph Data Augmentation Papers

This repository contains a list of papers on the Graph Data Augmentation, we categorize them based on their learning objectives and tasks.

We will try to make this list updated. If you found any error or any missed paper, please don't hesitate to open an issue or pull request.

Note by Tong (April 2024): I've been quite busy these days and it's kinda hard for me to keep track of all the recent literature. Hence, this list is probably a bit outdated since this year (2024), and any community contribution would be greatly appreciated :)

Materials

Survey Paper

Graph Data Augmentation for Graph Machine Learning: A Survey.

Tong Zhao, Wei Jin, Yozen Liu, Yingheng Wang, Gang Liu, Stephan Günneman, Neil Shah, and Meng Jiang.

If you find this repository helpful for your work, please kindly cite our paper.

@article{zhao2022graph,
  title={Graph Data Augmentation for Graph Machine Learning: A Survey},
  author={Zhao, Tong and Jin, Wei and Liu, Yozen and Wang, Yingheng and Liu, Gang and Günneman, Stephan and Shah, Neil and Jiang, Meng},
  journal={IEEE Data Engineering Bulletin},
  year={2023}
}

Tutorials

• SDM 2023: Augmentation Methods for Graph Learning

Graph data augmentation for (semi-)supervised learning

Node-level tasks

• Half-Hop: a Graph Upsampling Approach for Slowing Down Message Passing, in ICML 2023. [pdf]

• Local Augmentation for Graph Neural Networks, in ICML 2022. [pdf]

• Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping, in arXiv 2021. [pdf]

• FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning, in arXiv 2021. [pdf] [code]

• Topological Regularization for Graph Neural Networks Augmentation, in arXiv 2021. [pdf]

• Semi-Supervised and Self-Supervised Classification with Multi-View Graph Neural Networks, in CIKM 2021. [pdf]

• Metropolis-Hastings Data Augmentation for Graph Neural Networks, in NeurIPS 2021. [pdf]

• Action Sequence Augmentation for Early Graph-based Anomaly Detection, in CIKM 2021. [pdf] [code]

• Data Augmentation for Graph Neural Networks, in AAAI 2021. [pdf] [code]

• Automated Graph Representation Learning for Node Classification, in IJCNN 2021. [pdf]

• Mixup for Node and Graph Classification, in The WebConf 2021. [pdf] [code]

• Heterogeneous Graph Neural Network via Attribute Completion, in The WebConf 2021. [pdf]

• FLAG: Adversarial Data Augmentation for Graph Neural Networks, in arXiv 2020. [pdf] [code]

• GraphMix: Improved Training of GNNs for Semi-Supervised Learning, in arXiv 2020. [pdf] [code]

• Robust Graph Representation Learning via Neural Sparsification, in ICML 2020. [pdf]

• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification, in ICLR 2020. [pdf] [code]

• Graph Structure Learning for Robust Graph Neural Networks, in KDD 2020. [pdf] [code]

• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View, in AAAI 2020. [pdf]

• Diffusion Improves Graph Learning, in NeurIPS 2019. [pdf] [code]

Graph-level tasks

• Data-Centric Learning from Unlabeled Graphs with Diffusion Model, in NeurIPS 2023. [pdf] [code]

• Automated Data Augmentations for Graph Classification, in ICLR 2023. [pdf]

• Semi-Supervised Graph Imbalanced Regression, in KDD 2023. [pdf] [code]

• G-Mixup: Graph Data Augmentation for Graph Classification, in ICML 2022. [pdf] [code]

• Graph Rationalization with Environment-based Augmentations, in KDD 2022. [pdf] [code]

• Graph Augmentation Learning, in arXiv 2022. [pdf]

• GAMS: Graph Augmentation with Module Swapping, in arXiv 2022. [pdf]

• Graph Transplant: Node Saliency-Guided Graph Mixup with Local Structure Preservation, in AAAI 2022. [pdf]

• ifMixup: Towards Intrusion-Free Graph Mixup for Graph Classification, in arXiv, 2021. [pdf]

• Mixup for Node and Graph Classification, in The WebConf 2021. [pdf] [code]

• MoCL: Data-driven Molecular Fingerprint via Knowledge-aware Contrastive Learning from Molecular Graph, in KDD 2021. [pdf] [code]

• FLAG: Adversarial Data Augmentation for Graph Neural Networks, in arXiv 2020. [pdf] [code]

• GraphCrop: Subgraph Cropping for Graph Classification, in arXiv 2020. [pdf]

• M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification, in CIKM 2020 [pdf] and IEEE TNSE 2021. [pdf]

Edge-level tasks

• Knowledge Graph Completion with Counterfactual Augmentation, in TheWebConf 2023. [pdf]

• Learning from Counterfactual Links for Link Prediction, in ICML 2022. [pdf] [code]

• Adaptive Data Augmentation on Temporal Graphs, in NeurIPS 2021. [pdf]

• FLAG: Adversarial Data Augmentation for Graph Neural Networks, in arXiv 2020. [pdf] [code]

Graph data augmentation with self-supervised learning objectives

Contrastive learning

• Spectral Augmentation for Self-Supervised Learning on Graphs, in ICLR 2023. [pdf]

• Graph Self-supervised Learning with Accurate Discrepancy Learning, in NeurIPS 2022. [pdf] [code]

• Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative, in NeurIPS 2022. [code]

• Learning Graph Augmentations to Learn Graph Representations, in arXiv 2022. [pdf] [code]

• Fair Node Representation Learning via Adaptive Data Augmentation, in arXiv 2022. [pdf]

• Large-Scale Representation Learning on Graphs via Bootstrapping, in ICLR 2022. [pdf] [code]

• Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices, in The WebConf 2022. [pdf]

• Contrastive Self-supervised Sequential Recommendation with Robust Augmentation, in arXiv 2021. [pdf]

• Collaborative Graph Contrastive Learning: Data Augmentation Composition May Not be Necessary for Graph Representation Learning, in arXiv 2021. [pdf]

• Molecular Graph Contrastive Learning with Parameterized Explainable Augmentations, in BIBM 2021. [pdf]

• Self-Supervised GNN that Jointly Learns to Augment, in NeurIPS Workshop 2021. [pdf]

• InfoGCL: Information-Aware Graph Contrastive Learning, in NeurIPS 2021. [pdf]

• Adversarial Graph Augmentation to Improve Graph Contrastive Learning, in NeurIPS 2021. [pdf] [code]

• Graph Contrastive Learning with Adaptive Augmentation, in The WebConf 2021. [pdf] [code]

• Semi-Supervised and Self-Supervised Classification with Multi-View Graph Neural Networks, in CIKM 2021. [pdf]

• Graph Contrastive Learning Automated, in ICML 2021. [pdf] [code]

• Graph Data Augmentation based on Adaptive Graph Convolution for Skeleton-based Action Recognition, in ICCSNT 2021. [pdf]

• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning, in ICDM 2020. [pdf] [code]

• Contrastive Multi-View Representation Learning on Graphs, in ICML 2020. [pdf] [code]

• Graph Contrastive Learning with Augmentations, in NeurIPS 2020. [pdf] [code]

• Deep Graph Contrastive Representation Learning, in GRL+ Workshop @ICML 2020. [pdf] [code]

• Deep Graph Infomax, in ICLR 2019. [pdf] [code]

Consistency learning

• NodeAug: Semi-Supervised Node Classification with Data Augmentation, in KDD 2020. [pdf]

• Graph Random Neural Network for Semi-Supervised Learning on Graphs, in NeurIPS 2020. [pdf] [code]

Acknowledgement

This page is contributed and maintained by Tong Zhao (tzhao2@nd.edu), Gang Liu (gliu7@nd.edu), and Yingheng Wang (jakewyh@163.com).