Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Fast Inference of Removal-Based Node Influence (2403.08333v3)

Published 13 Mar 2024 in cs.LG and cs.AI

Abstract: Graph neural networks (GNNs) are widely utilized to capture the information spreading patterns in graphs. While remarkable performance has been achieved, there is a new trending topic of evaluating node influence. We propose a new method of evaluating node influence, which measures the prediction change of a trained GNN model caused by removing a node. A real-world application is, "In the task of predicting Twitter accounts' polarity, had a particular account been removed, how would others' polarity change?". We use the GNN as a surrogate model whose prediction could simulate the change of nodes or edges caused by node removal. Our target is to obtain the influence score for every node, and a straightforward way is to alternately remove every node and apply the trained GNN on the modified graph to generate new predictions. It is reliable but time-consuming, so we need an efficient method. The related lines of work, such as graph adversarial attack and counterfactual explanation, cannot directly satisfy our needs, since their problem settings are different. We propose an efficient, intuitive, and effective method, NOde-Removal-based fAst GNN inference (NORA), which uses the gradient information to approximate the node-removal influence. It only costs one forward propagation and one backpropagation to approximate the influence score for all nodes. Extensive experiments on six datasets and six GNN models verify the effectiveness of NORA. Our code is available at https://github.com/weikai-li/NORA.git.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (71)
  1. Robust Counterfactual Explanations on Graph Neural Networks. CoRR abs/2107.04086 (2021). arXiv:2107.04086 https://arxiv.org/abs/2107.04086
  2. Link and node removal in real social networks: a review. Frontiers in Physics 8 (2020), 228.
  3. Time and space complexity of graph convolutional networks. Accessed on: Dec 31 (2021).
  4. Simple and Deep Graph Convolutional Networks. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daumé III and Aarti Singh (Eds.). PMLR, 1725–1735. https://proceedings.mlr.press/v119/chen20v.html
  5. Understanding and Improving Graph Injection Attack by Promoting Unnoticeability. https://doi.org/10.48550/ARXIV.2202.08057
  6. A topological analysis of the Italian electric power grid. Physica A: Statistical mechanics and its applications 338, 1-2 (2004), 92–97.
  7. A Targeted Universal Attack on Graph Convolutional Network. CoRR abs/2011.14365 (2020). arXiv:2011.14365 https://arxiv.org/abs/2011.14365
  8. Pedro Domingos and Matt Richardson. 2001. Mining the Network Value of Customers. In Proceedings of the Seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (San Francisco, California) (KDD ’01). Association for Computing Machinery, New York, NY, USA, 57–66. https://doi.org/10.1145/502512.502525
  9. Neural Message Passing for Quantum Chemistry. CoRR abs/1704.01212 (2017). arXiv:1704.01212 http://arxiv.org/abs/1704.01212
  10. Information diffusion through blogspace. In Proceedings of the 13th international conference on World Wide Web. 491–501.
  11. Inductive Representation Learning on Large Graphs. CoRR abs/1706.02216 (2017). arXiv:1706.02216 http://arxiv.org/abs/1706.02216
  12. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
  13. P Holme. 2004. Efficient local strategies for vaccination and network attack. Europhysics Letters (EPL) 68, 6 (dec 2004), 908–914. https://doi.org/10.1209/epl/i2004-10286-2
  14. Open Graph Benchmark: Datasets for Machine Learning on Graphs. CoRR abs/2005.00687 (2020). arXiv:2005.00687 https://arxiv.org/abs/2005.00687
  15. Community-based influence maximization for viral marketing. Applied Intelligence 49 (2019), 2137–2150.
  16. Global Counterfactual Explainer for Graph Neural Networks. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. 141–149.
  17. Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning. pmlr, 448–456.
  18. A hybrid algorithm based on community detection and multi attribute decision making for influence maximization. Computers & Industrial Engineering 120 (2018), 234–250.
  19. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia. 675–678.
  20. Black-box Node Injection Attack for Graph Neural Networks. https://doi.org/10.48550/ARXIV.2202.09389
  21. Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning. https://doi.org/10.48550/ARXIV.2211.10782
  22. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  23. Thomas N. Kipf and Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. CoRR abs/1609.02907 (2016). arXiv:1609.02907 http://arxiv.org/abs/1609.02907
  24. The dynamics of viral marketing. ACM Transactions on the Web (TWEB) 1, 1 (2007), 5–es.
  25. Patterns of cascading behavior in large blog graphs. In Proceedings of the 2007 SIAM international conference on data mining. SIAM, 551–556.
  26. An influence maximization method based on crowd emotion under an emotion-based attribute social network. Information Processing & Management 59, 2 (2022), 102818.
  27. Yuchong Li and Qinghui Liu. 2021. A comprehensive review study of cyber-attacks and cyber security; Emerging trends and recent developments. Energy Reports 7 (2021), 8176–8186.
  28. Balanced influence maximization in attributed social network based on sampling. In Proceedings of the 13th International Conference on Web Search and Data Mining. 375–383.
  29. Deep graph representation learning and optimization for influence maximization. In International Conference on Machine Learning. PMLR, 21350–21361.
  30. A Learning Convolutional Neural Network Approach for Network Robustness Prediction. IEEE Transactions on Cybernetics (2022), 1–14. https://doi.org/10.1109/tcyb.2022.3207878
  31. CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks. CoRR abs/2102.03322 (2021). arXiv:2102.03322 https://arxiv.org/abs/2102.03322
  32. Parameterized Explainer for Graph Neural Network. CoRR abs/2011.04573 (2020). arXiv:2011.04573 https://arxiv.org/abs/2011.04573
  33. Adversarial Attack on Graph Neural Networks as An Influence Maximization Problem. CoRR abs/2106.10785 (2021). arXiv:2106.10785 https://arxiv.org/abs/2106.10785
  34. Clear: Generative counterfactual explanations on graphs. Advances in Neural Information Processing Systems 35 (2022), 25895–25907.
  35. More Effective Centrality-Based Attacks on Weighted Networks. https://doi.org/10.48550/ARXIV.2211.09345
  36. Efficient Estimation of Word Representations in Vector Space. arXiv:1301.3781 [cs.CL]
  37. Distributed Representations of Words and Phrases and their Compositionality. arXiv:1310.4546 [cs.CL]
  38. A billion-scale approximation algorithm for maximizing benefit in viral marketing. IEEE/ACM Transactions On Networking 25, 4 (2017), 2419–2429.
  39. Conditional attack strategy for real-world complex networks. Physica A: Statistical Mechanics and its Applications 530 (2019), 121561.
  40. Embedding-aided network dismantling. https://doi.org/10.48550/ARXIV.2208.01087
  41. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015).
  42. Efficient GNN Explanation via Learning Removal-based Attribution. arXiv:2306.05760 [cs.LG]
  43. ImageNet Large Scale Visual Recognition Challenge. arXiv:1409.0575 [cs.CV]
  44. Collective Classification in Network Data. AI Mag. 29 (2008), 93–106.
  45. Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).
  46. A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence. IEEE Access 9 (2021), 11974–12001. https://doi.org/10.1109/ACCESS.2021.3051315
  47. RLIM: representation learning method for influence maximization in social networks. International Journal of Machine Learning and Cybernetics 13, 11 (2022), 3425–3440.
  48. Adversarial attacks on graph neural networks via node injections: A hierarchical reinforcement learning approach. In Proceedings of the Web Conference 2020. 673–683.
  49. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1–9.
  50. Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning. In Proceedings of the ACM Web Conference 2022. ACM. https://doi.org/10.1145/3485447.3511948
  51. Single Node Injection Attack against Graph Neural Networks. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. ACM. https://doi.org/10.1145/3459637.3482393
  52. Deep reinforcement learning-based approach to tackle topic-aware influence maximization. Data Science and Engineering 5 (2020), 1–11.
  53. Graph Attention Networks. https://doi.org/10.48550/ARXIV.1710.10903
  54. Attacking Fake News Detectors via Manipulating News Social Engagement. arXiv:2302.07363 [cs.SI]
  55. Scalable Attack on Graph Data by Injecting Vicious Nodes. CoRR abs/2004.13825 (2020). arXiv:2004.13825 https://arxiv.org/abs/2004.13825
  56. Immunity of multiplex networks via acquaintance vaccination. Europhysics Letters 112, 4 (2015), 48002.
  57. Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, Online, 1942–1955. https://doi.org/10.18653/v1/2021.naacl-main.156
  58. TIMME: Twitter ideology-detection via multi-task multi-relational embedding. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2258–2268.
  59. Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. CoRR abs/1906.04214 (2019). arXiv:1906.04214 http://arxiv.org/abs/1906.04214
  60. Betweenness Approximation for Hypernetwork Dismantling with Hypergraph Neural Network. https://doi.org/10.48550/ARXIV.2203.03958
  61. GNNExplainer: Generating Explanations for Graph Neural Networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett (Eds.). 9240–9251. https://proceedings.neurips.cc/paper/2019/hash/d80b7040b773199015de6d3b4293c8ff-Abstract.html
  62. XGNN: Towards Model-Level Explanations of Graph Neural Networks. CoRR abs/2006.02587 (2020). arXiv:2006.02587 https://arxiv.org/abs/2006.02587
  63. On Explainability of Graph Neural Networks via Subgraph Explorations. CoRR abs/2102.05152 (2021). arXiv:2102.05152 https://arxiv.org/abs/2102.05152
  64. Network dynamic GCN influence maximization algorithm with leader fake labeling mechanism. IEEE Transactions on Computational Social Systems (2022).
  65. Jiazheng Zhang and Bang Wang. 2022. Dismantling Complex Networks by a Neural Model Trained from Tiny Networks. In Proceedings of the 31st ACM International Conference on Information Knowledge Management. ACM. https://doi.org/10.1145/3511808.3557290
  66. Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation. In Proceedings of the ACM Web Conference 2022. ACM. https://doi.org/10.1145/3485447.3512179
  67. Dimensional reweighting graph convolutional networks. arXiv preprint arXiv:1907.02237 (2019).
  68. TDGIA: Effective Injection Attacks on Graph Neural Networks. CoRR abs/2106.06663 (2021). arXiv:2106.06663 https://arxiv.org/abs/2106.06663
  69. Adversarial Attacks on Graph Neural Networks: Perturbations and Their Patterns. ACM Trans. Knowl. Discov. Data 14, 5, Article 57 (jun 2020), 31 pages. https://doi.org/10.1145/3394520
  70. Daniel Zügner and Stephan Günnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. CoRR abs/1902.08412 (2019). arXiv:1902.08412 http://arxiv.org/abs/1902.08412
  71. Adversarial Attacks on Neural Networks for Graph Data. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM. https://doi.org/10.1145/3219819.3220078

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets