Characterizing the Influence of Graph Elements

theoretical bounds on the estimation error of the edge and node influence on model parameters. We experimentally validated the accuracy and effectiveness of our influence functions by comparing its estimation with the actual influence obtained by model retraining. We showed in our experiments that our influence functions could be used to reliably identify edge and node with negative and positive influences on model performance. Finally, we demonstrated that our influence function could be applied to improve model performance and carry out adversarial attacks.

[1]  Hongfu Liu,et al.  Achieving Fairness at No Utility Cost via Data Reweighing , 2022, ICML.

[2]  Qiang Huang,et al.  GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks , 2020, IEEE Transactions on Knowledge and Data Engineering.

[3]  Jiarong Xu,et al.  Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning , 2021, NeurIPS Datasets and Benchmarks.

[4]  Xiangji Huang,et al.  Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation , 2021, AAAI.

[5]  Shuiwang Ji,et al.  On Explainability of Graph Neural Networks via Subgraph Explorations , 2021, ICML.

[6]  Hongfu Liu,et al.  On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections , 2021, ICLR.

[7]  C. Shi,et al.  Adversarial Label-Flipping Attack and Defense for Graph Neural Networks , 2020, 2020 IEEE International Conference on Data Mining (ICDM).

[8]  Yiran Chen,et al.  Evasion Attacks to Graph Neural Networks via Influence Function , 2020, ArXiv.

[9]  P'eter Mernyei,et al.  Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks , 2020, ArXiv.

[10]  Yulia Tsvetkov,et al.  Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions , 2020, ACL.

[11]  Jia Liu,et al.  Influence Function based Data Poisoning Attacks to Top-N Recommender Systems , 2020, WWW.

[12]  Xiangnan He,et al.  LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation , 2020, SIGIR.

[13]  Hong Zhu,et al.  Less Is Better: Unweighted Data Subsampling via Influence Function , 2019, AAAI.

[14]  Tsuyoshi Murata,et al.  Linear Graph Convolutional Model for Diagnosing Brain Disorders , 2019, COMPLEX NETWORKS.

[15]  Mariia Rizun,et al.  Knowledge Graph Application in Education: a Literature Review , 2019, Acta Universitatis Lodziensis. Folia Oeconomica.

[16]  Xiantong Zhen,et al.  Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking , 2019, ArXiv.

[17]  Sijia Liu,et al.  Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective , 2019, IJCAI.

[18]  Mihaela van der Schaar,et al.  Validating Causal Inference Models via Influence Functions , 2019, ICML.

[19]  Percy Liang,et al.  On the Accuracy of Influence Functions for Measuring Group Effects , 2019, NeurIPS.

[20]  J. Leskovec,et al.  GNNExplainer: Generating Explanations for Graph Neural Networks , 2019, NeurIPS.

[21]  Stephan Gunnemann,et al.  Adversarial Attacks on Graph Neural Networks via Meta Learning , 2019, ICLR.

[22]  Kilian Q. Weinberger,et al.  Simplifying Graph Convolutional Networks , 2019, ICML.

[23]  Yuan He,et al.  Graph Neural Networks for Social Recommendation , 2019, WWW.

[24]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[25]  Pietro Liò,et al.  Deep Graph Infomax , 2018, ICLR.

[26]  Stephan Günnemann,et al.  Adversarial Attacks on Node Embeddings via Graph Poisoning , 2018, ICML.

[27]  Michael I. Jordan,et al.  A Swiss Army Infinitesimal Jackknife , 2018, AISTATS.

[28]  Stephan Günnemann,et al.  Pitfalls of Graph Neural Network Evaluation , 2018, ArXiv.

[29]  Xinbing Wang,et al.  AceKG: A Large-scale Knowledge Graph for Academic Data Mining , 2018, CIKM.

[30]  Stephan Günnemann,et al.  Adversarial Attacks on Neural Networks for Graph Data , 2018, KDD.

[31]  Yixin Chen,et al.  Link Prediction Based on Graph Neural Networks , 2018, NeurIPS.

[32]  Cao Xiao,et al.  FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling , 2018, ICLR.

[33]  Eric Brochu,et al.  Optimal Sub-sampling with Influence Functions , 2017, NeurIPS.

[34]  Wlodek Zadrozny,et al.  Help me find a job: A graph-based approach for job recommendation at scale , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[35]  Deng Cai,et al.  Learning Graph-Level Representation for Drug Discovery , 2017, ArXiv.

[36]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[37]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[38]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[39]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[40]  Ichigaku Takigawa,et al.  Graph mining: procedure, application to drug discovery and recent advances. , 2013, Drug discovery today.

[41]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[42]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[43]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[44]  Ah Chung Tsoi,et al.  Graph neural networks for ranking Web pages , 2005, The 2005 IEEE/WIC/ACM International Conference on Web Intelligence (WI'05).

[45]  D. Pregibon.  Logistic Regression Diagnostics , 1981 .

[46]  F. Hampel.  The Influence Curve and Its Role in Robust Estimation , 1974 .