This repository aims to provide links to works in trustworthy graph neural networks. If you find this repo useful, please cite our survey A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability with:
@article{dai2022comprehensive,
title={A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability},
author={Dai, Enyan and Zhao, Tianxiang and Zhu, Huaisheng and Xu, Junjie and Guo, Zhimeng and Liu, Hui and Tang, Jiliang and Wang, Suhang},
journal={arXiv preprint arXiv:2204.08570},
year={2022}
}
- Adversarial Attacks and Defenses on Graphs: A Review and Empirical Study. SIGKDD Explorations 2020. [paper] [code]
- A Survey of Adversarial Learning on Graphs. arxiv, 2020. [paper]
- Adversarial Attacks and Defenses in Images, Graphs and Text: A Review. arxiv, 2019. [paper]
- Adversarial Attack and Defense on Graph Data: A Survey. arxiv 2018. [paper]
Dataset | Task | Labels | Sensitive Attributes | Link |
---|---|---|---|---|
Pokec-n | Node classificaiton | Job | Region | [code] |
Pokec-z | Node classificaiton | Job | Region | [code] |
NBA | Node classificaiton | Salary | Nationality | [code] |
German Credit | Node classificaiton | Credit Risk | Gender | [code] |
Recidivism | Node classificaiton | Bail | Race | [code] |
Credit Defaulter | Node classificaiton | Default | Age | [code] |
MovieLens | Link Prediction | - | Multi-attribute | [code] |
Link Prediction | - | Multi-attribute | [code] | |
Polblog | Link Prediction | - | Community | [code] |
Link Prediction | - | Politics | [code] | |
Link Prediction | - | Gender | [code] | |
Google+ | Link Prediction | - | Gender | [code] |
Dutch | Link Prediction | - | Gender | [code] |
Dataset | Type | Graphs | Avg. Nodes | Avg. Edges | Features |
---|---|---|---|---|---|
Coauthor | Authorship | 1 | 34493 | 247962 | 8415 |
ACM | Authorship | 1 | 3025 | 26256 | 1870 |
Social Networks | 1 | 4039 | 88234 | - | |
LastFM | Social Networks | 1 | 7624 | 27806 | 7824 |
Social Networks | 1 | 232965 | 57307946 | 602 | |
Flickr | Image | 1 | 89250 | 449878 | 500 |
PROTEINS | Bioinformatics | 1113 | 39.06 | 72.82 | 29 |
DD | Bioinformatics | 1178 | 284.32 | 715.66 | 89 |
ENZYMES | Bioinformatics | 600 | 32.63 | 62.14 | 21 |
NCI1 | Molecule | 4110 | 29.87 | 32.30 | 37 |
AIDS | Molecule | 2000 | 15.69 | 16.20 | 42 |
OVCAR-8H | Molecule | 4052 | 46.67 | 48.70 | 65 |
Dataset | Task | #Graphs | #Nodes | Link |
---|---|---|---|---|
BA-Shapes | Node classification | 1 | 700 | 4,110 |
BA-Community | Node classification | 1 | 1,400 | 8,920 |
Tree-Cycles | Node classification | 1 | 871 | 1,950 |
Tree-Grid | Node classification | 1 | 1,231 | 3,410 |
Syn-Cora | Node classification | 1 | 1,895 | 2,769 |
BA-2motifs | Graph classification | 1,000 | 25 | 51.4 |
Infection | Graph classification | 10 | 1000 | 3996 |
Graph-SST2 | Graph classification | 70,042 | 10.199 | 9.20 |
Graph-SST5 | Graph classification | 11,855 | 19.849 | 18.849 |
Graph-Twitter | Graph classification | 6,949 | 21.103 | 21.10 |
MUTAG | Graph classification | 188 | 19.79 | 17.93 |
- EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks WWW 2022. [paper], [code]
- Unbiased graph embedding with biased graph observations WWW 2022. [paper]
- CrossWalk: Fairness-enhanced Node Representation Learning AAAI 2022. [paper], [code]
- Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information WSDM 2021. [paper], [code]
- Towards a unified framework for fair and stable graph representation learning UAI 2021. [paper], [code]
- InFoRM: Individual Fairness on Graph Mining KDD 2020. [paper], [code]
- FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning IEEE Transactions on Artificial Intelligence 2021. [paper], [code]
- On dyadic fairness: Exploring and mitigating bias in graph connections ICLR 2021. [paper], [code]
- Individual fairness for graph neural networks: A ranking based approach KDD 2021. [paper], [code]
- Fairness-Aware Node Representation Learning KDD 2021. [paper]
- DeBayes: a Bayesian Method for Debiasing Network Embeddings ICML 2020. [paper], [code]
- Bursting the filter bubble: Fairness-aware network link prediction AAAI 2020. [paper], [code]
- Compositional Fairness Constraints for Graph Embeddings ICML 2019. [paper], [code]
- Fairwalk: Towards fair graph embedding IJCAI 2019. [paper], [code]
- Quantifying Privacy Leakage in Graph Embedding. Duddu, Vasisht, Antoine Boutet, and Virat Shejwalkar. MobiQuitous 2020. [paper], [code]
- Membership Inference Attack on Graph Neural Networks. Olatunji, Iyiola E., Wolfgang Nejdl, and Megha Khosla. TPS-ISA 2021. [paper], [code]
- Node-Level Membership Inference Attacks Against Graph Neural Networks. Xinlei He, Rui Wen, Yixin Wu, Michael Backes, Yun Shen, Yang Zhang. ArXiv 2021. [paper], [code]
- Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implications. Bang Wu, Xiangwen Yang, Shirui Pan, Xingliang Yuan. ICDM 2021. [paper], [code]
- Inference Attacks Against Graph Neural Networks. Zhang, Zhikun and Chen, Min and Backes, Michael and Shen, Yun and Zhang, Yang. USENIX Security 2022. [paper], [code]
- Stealing Links from Graph Neural Networks. Xinlei He, Jinyuan Jia, Michael Backes, Neil Zhenqiang Gong, Yang Zhang. USENIX Security 2021. [paper], [code]
- Graphmi: Extracting private graph data from graph neural networks. Zaixi Zhang, Qi Liu, Zhenya Huang, Hao Wang, Chengqiang Lu, Chuanren Liu, Enhong Chen. . [paper], [code]
- Model extraction attacks on graph neural networks: Taxonomy and realization. Bang Wu, Xiangwen Yang, Shirui Pan, Xingliang Yuan. ASIA CCS 2022,. [paper], [code]
- Model stealing attacks against inductive graph neural networks. Yun Shen, Xinlei He, Yufei Han, Yang Zhang. IEEE S&P 2022. [paper], [code]
- Releasing Graph Neural Networks with Differential Privacy. Iyiola E. Olatunji, Thorben Funke, Megha Khosla. ArXiv 2021. [paper], [code]
- Locally Private Graph Neural Networks. Sajadmanesh, Sina and Gatica-Perez, Daniel. CCS 2021. [paper], [code]
- DPNE: Differentially Private Network Embedding. Depeng Xu, Shuhan Yuan, Xintao Wu, and HaiNhat Phan. PKDD 2018. [paper], [code]
- Graph Embedding for Recommendation against Attribute Inference Attacks. Shijie Zhang, Hongzhi Yin, Tong Chen, Zi Huang, Lizhen Cui, Xiangliang Zhang. Web Conf. 2021. [paper], [code]
- FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation. Chuhan Wu, Fangzhao Wu, Yang Cao, Yongfeng Huang, Xing Xie. ArXiv 2021. [paper], [code]
- Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification. Chaochao Chen, Jun Zhou, Longfei Zheng, Huiwen Wu, Lingjuan Lyu, Jia Wu, Bingzhe Wu, Ziqi Liu, Li Wang, Xiaolin Zheng. ArXiv 2020. [paper], [code]
- Federated Social Recommendation with Graph Neural Network. Zhiwei Liu, Liangwei Yang, Ziwei Fan, Hao Peng, Philip S. Yu. TIST 2021. [paper], [code]
- SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks. Chaoyang He, Emir Ceyani, Keshav Balasubramanian, Murali Annavaram, Salman Avestimehr. ArXiv 2021. [paper], [code]
- Decentralized Federated Graph Neural Networks. Yang Pei1, Renxin Mao, Yang Liu, Chaoran Chen, Shifeng Xu, Feng Qiang. FTL-IJCAI 2021. [paper], [code]
- Federated Graph Classification over Non-IID Graphs. Han Xie, Jing Ma, Li Xiong, Carl Yang. NIPS 2021. [paper], [code]
- GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs. Binghui Wang, Ang Li, Hai Li, Yiran Chen. ArXiv 2020. [paper], [code]
- ASFGNN: Automated separated-federated graph neural network. Longfei Zheng, Jun Zhou, Chaochao Chen, Bingzhe Wu, Li Wang, Benyu Zhang. [paper], [code]
- Adversarial Privacy Preserving Graph Embedding against Inference Attack. Kaiyang Li, Guangchun Luo, Yang Ye, Wei Li, Shihao Ji, Zhipeng Cai. IEEE IoT 2020. [paper], [code]
- Information Obfuscation of Graph Neural Networks. Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi Jaakkola, Geoffrey Gordon, Stefanie Jegelka, Ruslan Salakhutdinov. ICML 2021. [paper], [code]
- Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective. Binghui Wang, Jiayi Guo, Ang Li, Yiran Chen, Hai Li. KDD 2021. [paper], [code]
- Towards Self-Explainable Graph Neural Network. CIKM 2021. [paper]
- ProtGNN: Towards Self-Explaining Graph Neural Networks. AAAI 2022. [paper]
- Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism. Arxiv 2022. [paper]
- KerGNNs: Interpretable Graph Neural Networks with Graph Kernels. AAAI 2022. [paper]
- Gnnexplainer: Generating explanations for graph neural networks. Ying Rex, Bourgeois Dylan, You Jiaxuan, Zitnik Marinka, Leskovec Jure. NeurIPS 2019. [paper] [code]
- Explainability methods for graph convolutional neural networks. Pope Phillip E, Kolouri Soheil, Rostami Mohammad, Martin Charles E, Hoffmann Heiko. CVPR 2019.[paper]
- Parameterized Explainer for Graph Neural Network. Luo Dongsheng, Cheng Wei, Xu Dongkuan, Yu Wenchao, Zong Bo, Chen Haifeng, Zhang Xiang. NeurIPS 2020. [paper] [code]
- Xgnn: Towards model-level explanations of graph neural networks. Yuan Hao, Tang Jiliang, Hu Xia, Ji Shuiwang. KDD 2020. [paper].
- Evaluating Attribution for Graph Neural Networks. Sanchez-Lengeling Benjamin, Wei Jennifer, Lee Brian, Reif Emily, Wang Peter, Qian Wesley, McCloskey Kevin, Colwell Lucy, Wiltschko Alexander. NeurIPS 2020.[paper]
- PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks. Vu Minh, Thai My T.. NeurIPS 2020. [paper]
- Causal Screening to Interpret Graph Neural Networks. [paper]
- GraphSVX: Shapley Value Explanations for Graph Neural Networks. ECML PKDD 2021. [paper]
- GNES: Learning to Explain Graph Neural Networks. ICDM 2021. [paper]
- Generative Causal Explanations for Graph Neural Networks. ICML 2021. [paper]
- On Explainability of Graph Neural Networks via Subgraph Explorations. ICML 2021. [paper]
- Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks. [paper]
- Robust Counterfactual Explanations on Graph Neural Networks. Neurips 2021. [paper]
- When Comparing to Ground Truth is Wrong: On Evaluating GNN Explanation Methods. KDD 2021. [paper]
- Towards Multi-Grained Explainability for Graph Neural Networks. Neurips 2021. [paper]
- Reinforcement Learning Enhanced Explainer for Graph Neural Networks. Neurips 2021. [paper]
- Discovering Invariant Rationales for Graph Neural Networks. ICLR 2022. [paper]
- Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks. Arxiv 2021. [paper]
- On Consistency in Graph Neural Network Interpretation. Arxiv 2022. [paper]
- GRAPHSHAP: Motif-based Explanations for Black-box Graph Classifiers. Arxiv 2022. [paper]
- MotifExplainer: a Motif-based Graph Neural Network Explainer. Arxiv 2022. [paper]
- Reinforced Causal Explainer for Graph Neural Networks. TPAMI 2022. [paper]
- CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks. AISTATS 2022 [paper]
- Prototype-Based Explanations for Graph Neural Networks. AAAI 2022. [paper]
- FlowX: Towards Explainable Graph Neural Networks via Message Flows. OpenReview 2021. [paper]
- Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin. IJCAI 2019. [paper] [code]
- Fast Gradient Attack on Network Embedding. Jinyin Chen, Yangyang Wu, Xuanheng Xu, Yixian Chen, Haibin Zheng, Qi Xuan. arxiv 2018. [paper] [code]
- Adversarial Examples on Graph Data: Deep Insights into Attack and Defense. Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu. IJCAI 2019. [paper] [code]
- Robustness of Graph Neural Networks at Scale. NeurIPS 2021. [paper] [code]
- Adversarial Attack on Large Scale Graph. TKDE 2021. [paper]
- Scalable Attack on Graph Data by Injecting Vicious Nodes. arxiv 2020. [paper]
- Graph Backdoor. Zhaohan Xi, Ren Pang, Shouling Ji, Ting Wang. USENIX 2021. [paper]
- Backdoor Attacks to Graph Neural Networks. Zaixi Zhang, Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong. arxiv 2020. paper
- A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Models. Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Wenwu Zhu, Junzhou Huang. AAAI 2020. [paper] [code]
- Adversarial Attacks on Node Embeddings via Graph Poisoning. Aleksandar Bojchevski, Stephan Günnemann. ICML 2019. [paper] [code]
- Adversarial Attack on Graph Structured Data. [paper] [code]
- Adversarial Attacks on Neural Networks for Graph Data. Daniel Zügner, Amir Akbarnejad, Stephan Günnemann. KDD 2018. [paper] [code]
- Attacking Graph Neural Networks at Scale. Simon Geisler, Daniel Zügner, Aleksandar Bojchevski, Stephan Günnemann. AAAI workshop 2021. [paper]
- Attacking Graph-based Classification via Manipulating the Graph Structure. Binghui Wang, Neil Zhenqiang Gong. CCS 2019. [paper]
- Adversarial Attacks on Graph Neural Networks via Meta Learning. Daniel Zugner, Stephan Gunnemann. ICLR 2019. [paper] [code]
- Adversarial attacks on neural networks for graph data KDD 2018. [paper] [code]
- Attacking Graph Convolutional Networks via Rewiring. Yao Ma, Suhang Wang, Lingfei Wu, Jiliang Tang. arxiv 2019. [paper]
- Adversarial attacks on graph neural networks via node injections: A hierarchical reinforcement learning approach. WWW 2020 [paper]
- Towards More Practical Adversarial Attacks on Graph Neural Networks. Jiaqi Ma, Shuangrui Ding, Qiaozhu Mei. NeurIPS 2020. [paper] [code]
- Single Node Injection Attack against Graph Neural Networks CIKM 2021. [[Paper]] [[code]]
- Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels arxiv 2022. [[Paper]] [[code]]
- Adversarial training methods for network embedding. WWW 2019. [paper] [code]
- Robustness of Graph Neural Networks at Scale. NeurIPS 2021. [paper] [code]
- Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin. IJCAI 2019. [paper] [code]
- Adversarial Attack on Graph Structured Data. [paper] [code]
- Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure Fuli Feng, Xiangnan He, Jie Tang, Tat-Seng Chua. TKDE 2019. [paper]
- GraphDefense: Towards Robust Graph Convolutional Networks. Xiaoyun Wang, Xuanqing Liu, Cho-Jui Hsieh. arxiv 2019. [paper]
- All You Need is Low (Rank): Defending Against Adversarial Attacks on Graphs. Negin Entezari, Saba Al-Sayouri, Amirali Darvishzadeh, and Evangelos E. Papalexakis. WSDM 2020. [paper] [code]
- GNNGuard: Defending Graph Neural Networks against Adversarial Attacks. NeurIPS 2020. [paper]
- Node Similarity Preserving Graph Convolutional Networks. WSDM 2021. [paper] [code]
- Robust Graph Neural Network Against Poisoning Attacks via Transfer Learning. Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang. WSDM 2020. [paper]
- Robust Graph Convolutional Networks Against Adversarial Attacks. Dingyuan Zhu, Ziwei Zhang, Peng Cui, Wenwu Zhu. KDD 2019. [paper]
- Adversarial Examples on Graph Data: Deep Insights into Attack and Defense. Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu. IJCAI 2019. [paper] [code]
- Learning to drop: Robust graph neural network via topological denoising. WSDM 2021. [[paper]] [[code]]
- Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels. WSDM 2022. [[paper]] [[code]]
- Graph Structure Learning for Robust Graph Neural Networks. Wei Jin, Yao Ma, Xiaorui Liu, Xianfeng Tang, Suhang Wang, Jiliang Tang. KDD 2020. [paper] [code]
- Can Adversarial Network Attack be Defended? arxiv 2019. [[paper]] [[code]]
- Learning robust representations with graph denoising policy network. ICDM 2019. [[paper]] [[code]]
- Batch Virtual Adversarial Training for Graph Convolutional Networks. Zhijie Deng, Yinpeng Dong, Jun Zhu. ICML 2019 Workshop. [paper]
- Understanding structural vulnerability in graph convolutional networks arxiv 2021. [[paper]] [[code]]
- Towards Self-Explainable Graph Neural Network. CIKM 2021. [[paper]] [[code]]
- Graph Contrastive Learning with Augmentations. NeurIPS 2020. [paper] [code]
- Robust Unsupervised Graph Representation Learning via Mutual Information Maximization arxiv 2022. [[paper]]
- Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks. NeurIPS 2020. [paper] [code]
- Adversarial Immunization for Improving Certifiable Robustness on Graphs. Arxiv 2020. [paper]
- Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation. Arxiv 2020. [paper]
- Efficient Robustness Certificates for Graph Neural Networks via Sparsity-Aware Randomized Smoothing. ICML 2020. [paper] [code]
- Certifiable Robustness of Graph Convolutional Networks under Structure Perturbations. KDD 2020. [paper] [code]
- Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing. Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Neil Zhenqiang Gong. WWW 2020. [paper]
- Certifiable Robustness to Graph Perturbations. Aleksandar Bojchevski, Stephan Günnemann. NeurIPS 2019. [paper][code]
- Certifiable Robustness and Robust Training for Graph Convolutional Networks. Daniel Zügner Stephan Günnemann. KDD 2019. [paper] [code]