This is a collection of resources related to trustworthy graph neural networks.
- Related concepts
- Papers
- Trustworthy Graph Neural Networks: Aspects, Methods and Trends. He Zhang, Bang Wu, Xingliang Yuan, Shirui Pan, Hanghang Tong, Jian Pei. 2022. paper
- A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability. Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo, Hui Liu, Jiliang Tang, Suhang Wang. 2022. paper
- A Comprehensive Survey on Graph Neural Networks. Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu. 2019. paper
- Graph Neural Networks: Foundations, Frontiers, and Applications. Lingfei Wu, Peng Cui, Jian Pei, Liang Zhao. 2022. book
- Trustworthy AI: A computational perspective. Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, Jiliang Tang. 2021. paper
- Trustworthy AI: from principles to practices. Bo Li], Peng Qi, Bo Liu, Shuai Di, Jingen Liu, Jiquan Pei, Jinfeng Yi, Bowen Zhou. 2021 paper
- Trustworthy Machine Learning. Kush R. Varshney. 2022. book
Here we only list some papers. For other studies, please visit our Survey on Trustworthy GNNs.
- Adversarial attack on graph structured data. ICML 2018. paper
- Topology attack and defense for graph neural networks: An optimization perspective. IJCAI 2019. paper
- Adversarial examples for graph data: Deep insights into attack and defense. IJCAI 2019. paper
- Fast gradient attack on network embedding. Arxiv 2018. paper
- Derivative-free optimization adversarial attacks for graph convolutional networks. PeerJ Computer Science 2021. paper
- Adversarial attacks on graph neural networks via node injections: A hierarchical reinforcement learning approach. WWW 2020. paper
- Adversarial attacks on neural networks for graph data. KDD 2018. paper
- All you need is low (rank): Defending against adversarial attacks on graphs. WSDM 2020. paper
- Graph structure learning for robust graph neural networks. KDD 2020. paper
- Graph sanitation with application to node classification. WWW 2022. paper
- Robust graph convolutional networks against adversarial attacks. KDD 2019. paper
- Transferring robustness for graph neural network against poisoning attacks. WSDM 2020. paper
- Defending graph convolutional networks against adversarial attacks. IEEE ICASSP 2020. paper
- Gnnguard: Defending graph neural networks against adversarial attacks. NeurIPS 2020. paper
- Graph adversarial training: Dynamically regularizing based on graph structure. IEEE TKDE 2021. paper
- Robust training of graph convolutional networks via latent perturbation. PKDD 2020. paper
- Topology attack and defense for graph neural networks: An optimization perspective. IJCAI 2019. paper
- Certifiable robustness to graph perturbations. NeurIPS 2019. paper
- Certifiable robustness and robust training for graph convolutional networks. KDD 2019. paper
- Adversarial immunization for certifiable robustness on graphs. WSDM 2021. paper
- Comparing and detecting adversarial attacks for graph deep learning. ICLR 2019. paper
- Convolutional networks on graphs for learning molecular fingerprints. NeurIPS 2015. paper
- Substructure assembling network for graph classification. AAAI 2018. paper
- Towards explainable representation of time-evolving graphs via spatial-temporal graph attention networks. CIKM 2019. paper
- Towards self-explainable graph neural network. CIKM 2021. paper
- Protgnn: Towards self-explaining graph neural networks. AAAI 2022. paper
- Motif-driven contrastive learning of graph representations. AAAI 2021. paper
- Discovering invariant rationales for graph neural networks. ICLR 2022. paper
- Graph information bottleneck for subgraph recognition. ICLR 2021. paper
- Explainability techniques for graph convolutional networks. ICML 2019. paper
- Explainability methods for graph convolutional neural networks. CVPR 2019. paper
- Gnnexplainer: Generating explanations for graph neural networks. NeurIPS 2019. paper
- Parameterized explainer for graph neural network. NeurIPS 2020. paper
- Hard masking for explaining graph neural networks. OpenReview 2021. paper
- Causal screening to interpret graph neural networks. OpenReview 2020. paper
- Interpreting graph neural networks for NLP with differentiable edge masking. ICLR 2021. paper
- On explainability of graph neural networks via subgraph explorations. ICML 2021. paper
- Cf-gnnexplainer: Counterfactual explanations for graph neural networks. AISTATS 2022. paper
- Robust counterfactual explanations on graph neural networks. NeurIPS 2021. paper
- Towards multi-grained explainability for graph neural networks. NeurIPS 2021. paper
- Learning and evaluating graph neural network explanations based on counterfactual and factual reasoning. WWW 2022. paper
- Graphlime: Local interpretable model explanations for graph neural networks. Arxiv 2020. paper
- Relex: A model-agnostic relational model explainer. AIES 2021. paper
- Pgm-explainer: Probabilistic graphical model explanations for graph neural networks. NeurIPS 2020. paper
- Higher-order explanations of graph neural networks via relevant walks. TPAMI 2021. paper
- XGNN: towards model-level explanations of graph neural networks. KDD 2020. paper
- Reinforcement learning enhanced explainer for graph neural networks. NeurIPS 2021. paper
- Orphicx: A causality-inspired latent variable model for interpreting graph neural networks. CVPR 2022. paper
- DEGREE: Decomposition based explanation for graph neural networks. ICLR 2021. paper
- Counterfactual graphs for explainable classification of brain networks. KDD 2021. paper
- Generative causal explanations for graph neural networks. ICML 2021. paper
- Model extraction attacks on graph neural networks: Taxonomy and realization. AsiaCCS 2022. paper
- Learning discrete structures for graph neural networks. ICML 2019. paper
- Quantifying privacy leakage in graph embedding. MobiQuitous 2020. paper
- Node-level membership inference attacks against graph neural networks. Arxiv 2021. paper
- Stealing links from graph neural networks. USENIX Security Symposium 2021. paper
- Adapting membership inference attacks to GNN for graph classification: Approaches and implications. IEEE ICDM 2021. paper
- Membership inference attacks on knowledge graphs. Arxiv 2021. paper
- Inference attacks against graph neural networks. USENIX Security Symposium 2022. paper
- Graphmi: Extracting private graph data from graph neural networks. IJCAI 2021. paper
- Linkteller: Recovering private edges from graph neural networks via influence analysis. IEEE S&P 2022. paper
- Privacy-preserving representation learning on graphs: A mutual information perspective. KDD 2021. paper
- Federated dynamic graph neural networks with secure aggregation for video-based distributedsurveillance. IEEE TIST 2022. paper
- Spreadgnn: Serverless multi-task federated learning for graph neural networks. Arxiv 2021. paper
- Federated graph classification over non-iid graphs. NeurIPS. paper
- A federated multigraph integration approach for connectional brain template learning. ML-CDS 2021. paper
- Federated learning of molecular properties in a heterogeneous setting. Arxiv 2021. paper
- STFL: A temporal-spatial federated learning framework for graph neural networks. Arxiv 2021. paper
- Fedgnn: Federated graph neural network for privacy-preserving recommendation. Arxiv 2021. paper
- Federated social recommendation with graph neural network. Arxiv 2021. paper
- A vertical federated learning framework for graph convolutional network. Arxiv 2021. paper
- Vertically federated graph neural network for privacypreserving node classification. Arxiv 2020. paper
- ASFGNN: automated separated-federated graph neural network. Peer-to-Peer Networking and Applications 2021. paper
- Graphfl: A federated learning framework for semi-supervised node classification on graphs. Arxiv 2020. paper
- Fedgl: Federated graph learning framework with global self-supervision. Arxiv 2021. paper
- Cross-node federated graph neural network for spatio-temporal data modeling. KDD 2021. paper
- Subgraph federated learning with missing neighbor generation. NeurIPS 2021. paper
- Fedgraph: Federated graph learning with intelligent sampling. IEEE TPDS 2022. paper
- Towards representation identical privacy-preserving graph neural network via split learning. Arxiv 2021. paper
- Fedgraphnn: A federated learning system and benchmark for graph neural networks. Arxiv 2021. paper
- Locally private graph neural networks. ACM CCS 2021. paper
- Graph embedding for recommendation against attribute inference attacks. WWW 2021. paper
- Netfense: Adversarial defenses against privacy attacks on neural networks for graph data. IEEE TKDE 2021. paper
- Information obfuscation of graph neural networks. ICML 2021. paper
- Adversarial privacypreserving graph embedding against inference attack. IEEE ITJ 2021. paper
- Compositional fairness constraints for graph embeddings. ICML 2019. paper
- Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. WSDM 2021. paper
- Towards a unified framework for fair and stable graph representation learning. UAI 2021. paper
- EDITS: modeling and mitigating data bias for graph neural networks. WWW 2022. paper
- Inform: Individual fairness on graph mining. KDD 2020. paper
- On dyadic fairness: Exploring and mitigating bias in graph connections. ICLR 2021. paper
- Fairdrop: Biased edge dropout for enhancing fairness in graph representation learning. IEEE TAI 2021. paper
- Individual fairness for graph neural networks: A ranking based approach. KDD 2021. paper
- A pipeline for fair comparison of graph neural networks in node classification tasks. Arxiv 2020. paper
- A novel genetic algorithm with hierarchical evaluation strategy for hyperparameter optimisation of graph neural networks. Arxiv 2021. paper
- Bag of tricks of semi-supervised classification with graph neural networks. Arxiv 2021. paper
- Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study. IEEE TPAMI 2022. paper
- A pipeline for fair comparison of graph neural networks in node classification tasks. Arxiv 2020. paper
- A fair comparison of graph neural networks for graph classification. Arxiv 2019. paper
- HASHTAG: hash signatures for online detection of fault-injection attacks on deep neural networks. ICCAD 2021. paper
- Sensitive-sample fingerprinting of deep neural networks. CVPR 2019. paper
- Proof-of-learning: Definitions and practice. IEEE S&P 2021. paper
- Proof of learning (pole): Empowering machine learning with consensus building on blockchains (demo). AAAI 2021. paper
- GraphSAINT: Graph Sampling Based Inductive Learning Method. ICLR 2020. paper
- Gnnautoscale: Scalable and expressive graph neural networks via historical embeddings. ICML 2021. paper
- Simplifying graph convolutional networks. ICML 2019. paper
- Training graph neural networks with 1000 layers. ICML 2021. paper
- Pinnersage: Multi-modal user embedding framework for recommendations at pinterest. KDD 2020. paper
- ETA prediction with graph neural networks in google maps. CIKM 2021. paper
- # Efficient Data Loader for Fast Sampling-Based GNN Training on Large Graphs. IEEE TPDS 2021. paper
- On self-distilling graph neural network. IJCAI 2021. paper
- Graph-free knowledge distillation for graph neural networks. IJCAI 2021. paper
- Tinygnn: Learning efficient graph neural networks. KDD 2020. paper
- A unified lottery ticket hypothesis for graph neural networks. ICML 2021. paper
- Graph normalizing flows. NeurIPS 2019. paper
- Binary graph neural networks. CVPR 2021. paper
- Degree-quant: Quantization-aware training for graph neural networks. ICLR 2021. paper
- Fast graph representation learning with PyTorch Geometric. ICLR 2019. paper
- Deep graph library: Towards efficient and scalable deep learning on graphs. ICLR 2019. paper
- Engn: A high-throughput and energy-efficient accelerator for large graph neural networks. IEEE TC 2021. paper
- Hygcn: A GCN accelerator with hybrid architecture. HPCA 2020. paper
- Characterizing and understanding gcns on GPU. IEEE CAL. paper
- Alleviating irregularity in graph analytics acceleration: a hardware/software co-design approach. MICRO 2019. paper
- Accelerating large scale real-time GNN inference using channel pruning. VLDB Endowment 2021. paper
- G-cos: Gnnaccelerator co-search towards both better accuracy and efficiency. IEEE ICCAD. paper
- How neural networks extrapolate: From feedforward to graph neural networks. ICLR 2021. paper
- Explainability-based backdoor attacks against graph neural networks. WiseML 2021. paper
- Jointly attacking graph neural network and its explanations. Arxiv 2021. paper
- Towards a unified framework for fair and stable graph representation learning. UAI 2021. paper
- Compositional fairness constraints for graph embeddings. ICML 2019. paper
- Say no to the discrimination: Learning fair graph neural networks with limited sensitive attribute information. WSDM 2021. paper
- Discrete-valued neural communication. NeurIPS 2021. paper
- Graph structure learning for robust graph neural networks. KDD 2020. paper
- Defensevgae: Defending against adversarial attacks on graph data via a variational graph autoencoder. Arxiv 2020. paper
- Robust graph convolutional networks against adversarial attacks. KDD 2019. paper
- Transferring robustness for graph neural network against poisoning attacks. WSDM 2020. paper
- Extract the knowledge of graph neural networks and go beyond it: An effective knowledge distillation framework. WWW 2021. paper
- Privacy-preserving representation learning on graphs: A mutual information perspective. KDD 2021. paper
- Topological uncertainty: Monitoring trained neural networks through persistence of activation graphs. IJCAI 2021. paper
If you need more details, please visit the Survey on Trustworthy GNNs.
@article{DBLP:journals/corr/abs-2205-07424,
author = {He Zhang and
Bang Wu and
Xingliang Yuan and
Shirui Pan and
Hanghang Tong and
Jian Pei},
title = {Trustworthy Graph Neural Networks: Aspects, Methods and Trends},
journal = {CoRR},
volume = {abs/2205.07424},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.07424},
doi = {10.48550/arXiv.2205.07424},
eprinttype = {arXiv},
eprint = {2205.07424}
}