Abstract
Anchor link prediction across social networks plays an important role in multiple social network analysis. Traditional methods rely heavily on user privacy information or high-quality network topology information. These methods are not suitable for multiple social networks analysis in real-life. Deep learning methods based on graph embedding are restricted by the impact of the active privacy protection policy of users on the graph structure. In this paper, we propose a novel method which neutralizes the impact of users’ evasion strategies. First, graph embedding with conditional estimation analysis is used to obtain a robust embedding vector space. Secondly, cross-network features space for supervised learning is constructed via the constraints of cross-network feature collisions. The combination of robustness enhancement and cross-network feature collisions constraints eliminate the impact of evasion strategies. Extensive experiments on large-scale real-life social networks demonstrate that the proposed method significantly outperforms the state-of-the-art methods in terms of precision, adaptability, and robustness for the scenarios with evasion strategies.
- [1] . 2015. GraRep: Learning graph representations with global structural information. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. 891–900.Google Scholar
Digital Library
- [2] . 2016. Deep neural networks for learning graph representations. Proceedings of the AAAI Conference on Artificial Intelligence 30, 1 (
Feb. 2016).Google ScholarCross Ref
- [3] . 2016. BASS: A bootstrapping approach for aligning heterogenous social networks. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 459–475.Google Scholar
Digital Library
- [4] . 2020. Multi-level graph convolutional networks for cross-platform anchor link prediction. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1503–1511.Google Scholar
Digital Library
- [5] . 2019. Can adversarial network attack be defended?CoRR abs/1903.05994 (2019).
arXiv:1903.05994 http://arxiv.org/abs/1903.05994.Google Scholar - [6] . 2018. Fast gradient attack on network embedding. ArXiv abs/1809.02797 (2018).Google Scholar
- [7] . 2019. Deep active learning for anchor user prediction. arXiv preprint arXiv:1906.07318 (2019).Google Scholar
- [8] . 2019. Cross-network embedding for multi-network alignment. In The World Wide Web Conference. 273–284.Google Scholar
Digital Library
- [9] . 2010. Community detection in graphs. Physics Reports 486, 3–5 (2010), 75–174.Google Scholar
Cross Ref
- [10] . 2020. Stacking models for nearly optimal link prediction in complex networks. Proceedings of the National Academy of Sciences 117, 38 (2020), 23393–23400.Google Scholar
Cross Ref
- [11] . 2018. Graph embedding techniques, applications, and performance: A survey. Knowledge-Based Systems 151 (2018), 78–94.Google Scholar
Cross Ref
- [12] . 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 855–864.Google Scholar
Digital Library
- [13] . 2020. One model to rule them all in network science?Proceedings of the National Academy of Sciences 117, 41 (2020), 25195–25197.Google Scholar
Cross Ref
- [14] . 2009. Missing and spurious interactions and the reconstruction of complex networks. Proceedings of the National Academy of Sciences 106, 52 (2009), 22073–22078.Google Scholar
Cross Ref
- [15] . 2018. Regal: Representation learning-based graph alignment. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 117–126.Google Scholar
Digital Library
- [16] . 2012. Rolx: Structural role extraction & mining in large graphs. In Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1231–1239.Google Scholar
Digital Library
- [17] . 2002. Latent space approaches to social network analysis. Journal of the American Statistical Association 97, 460 (2002), 1090–1098.Google Scholar
Cross Ref
- [18] . 2011. Identifying users across social tagging systems. Proceedings of the International AAAI Conference on Web and Social Media 5, 1 (
Jul. 2011), 522–525.Google ScholarCross Ref
- [19] . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).Google Scholar
- [20] . 2016. The ethics of smart cities and urban science. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences 374, 2083 (2016), 20160115.Google Scholar
Cross Ref
- [21] . 2011. Network similarity decomposition (NSD): A fast and scalable approach to network alignment. IEEE Transactions on Knowledge and Data Engineering 24, 12 (2011), 2232–2243.Google Scholar
Digital Library
- [22] . 2013. Inferring anchor links across multiple heterogeneous social networks. In Proceedings of the 22nd ACM International Conference on Information & Knowledge Management. 179–188.Google Scholar
Digital Library
- [23] . 2014. Neural word embedding as implicit matrix factorization. Advances in Neural Information Processing Systems 27 (2014), 2177–2185.Google Scholar
Digital Library
- [24] . 2019. Adversarial learning for weakly-supervised social network alignment. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 996–1003.Google Scholar
Digital Library
- [25] . 2021. RLINK: Deep reinforcement learning for user identity linkage. World Wide Web 24, 1 (2021), 85–103.Google Scholar
Cross Ref
- [26] . 2013. What’s in a name? An unsupervised approach to link users across communities. In Proceedings of the Sixth ACM International Conference on Web Search and Data Mining. 495–504.Google Scholar
Digital Library
- [27] . 2016. Aligning users across social networks using network embedding. In IJCAI. 1774–1780.Google Scholar
- [28] . 2019. Structural representation learning for user alignment across social networks. IEEE Transactions on Knowledge and Data Engineering 32, 9 (2019), 1824–1837.Google Scholar
- [29] . 2012. Studying user footprints in different online social networks. In 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. IEEE, 1065–1070.Google Scholar
Digital Library
- [30] . 2015. Context-adaptive matrix factorization for multi-context recommendation. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. 901–910.Google Scholar
Digital Library
- [31] . 2016. Predict anchor links across social networks via an embedding approach. In IJCAI, Vol. 16. 1823–1829.Google Scholar
- [32] . 2017. Strategic social network analysis. In Thirty-First AAAI Conference on Artificial Intelligence.Google Scholar
Digital Library
- [33] . 2016. Asymmetric transitivity preserving graph embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1105–1114.Google Scholar
Digital Library
- [34] . 2014. DeepWalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 701–710.Google Scholar
Digital Library
- [35] . 2022. Predicting future links with new nodes in temporal academic networks. Journal of Physics: Complexity (2022).Google Scholar
Cross Ref
- [36] . 2019. Link prediction for tree-like networks. Chaos: An Interdisciplinary Journal of Nonlinear Science 29, 6 (2019), 061103.Google Scholar
Cross Ref
- [37] . 2022. Link prediction for long-circle-like networks. Physical Review E 105, 2 (2022), 024311.Google Scholar
Cross Ref
- [38] . 2019. PAAE: A unified framework for predicting anchor links with adversarial embedding. In 2019 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 682–687.Google Scholar
Cross Ref
- [39] . 2016. A survey of heterogeneous information network analysis. IEEE Transactions on Knowledge and Data Engineering 29, 1 (2016), 17–37.Google Scholar
Digital Library
- [40] . 2019. DNA: Dynamic social network alignment. In 2019 IEEE International Conference on Big Data (Big Data). IEEE, 1224–1231.Google Scholar
Cross Ref
- [41] . 2014. Mapping users across networks by manifold alignment on hypergraph. Proceedings of the AAAI Conference on Artificial Intelligence 28, 1 (
Jun. 2014).Google ScholarCross Ref
- [42] . 2015. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web. 1067–1077.Google Scholar
Digital Library
- [43] . 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 86 (2008), 2579–2605.Google Scholar
- [44] . 2016. Structural deep network embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1225–1234.Google Scholar
Cross Ref
- [45] . 2019. Anchor link prediction across attributed networks via network embedding. Entropy 21, 3 (2019), 254.Google Scholar
Cross Ref
- [46] . 2019. User identity linkage across social networks via linked heterogeneous network embedding. World Wide Web 22, 6 (2019), 2611–2632.Google Scholar
Cross Ref
- [47] . 2020. Hiding in multilayer networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 1021–1028.Google Scholar
Cross Ref
- [48] . 2018. Hiding individuals and communities in a social network. Nature Human Behaviour 2, 2 (2018), 139–147.Google Scholar
Cross Ref
- [49] . 2018. Attack tolerance of link prediction algorithms: How to hide your relations in a social network. arXiv preprint arXiv:1809.00152 (2018).Google Scholar
- [50] . 2014. Overlapping communities explain core–periphery organization of networks. Proc. IEEE 102, 12 (2014), 1892–1902.Google Scholar
Cross Ref
- [51] . 2019. Target defense against link-prediction-based attacks via evolutionary perturbations. IEEE Transactions on Knowledge and Data Engineering (2019).Google Scholar
Digital Library
- [52] . 2013. Connecting users across social media sites: A behavioral-modeling approach. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 41–49.Google Scholar
Digital Library
- [53] . 2019. Integrated anchor and social link predictions across multiple social networks. Knowledge and Information Systems 60, 1 (2019), 303–326.Google Scholar
Digital Library
- [54] . 2014. Meta-path based multi-network collective link prediction. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1286–1295.Google Scholar
Digital Library
- [55] . 2018. DeepLink: A deep learning approach for user identity linkage. In IEEE INFOCOM 2018-IEEE Conference on Computer Communications. IEEE, 1313–1321.Google Scholar
Digital Library
- [56] . 2007. Bipartite network projection and personal recommendation. Physical Review E 76, 4 (2007), 046115.Google Scholar
Cross Ref
- [57] . 2017. Structure based user identification across social networks. IEEE Transactions on Knowledge and Data Engineering 30, 6 (2017), 1178–1191.Google Scholar
Cross Ref
- [58] . 2019. Robust graph convolutional networks against adversarial attacks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1399–1407.Google Scholar
Digital Library
Index Terms
A Novel Cross-Network Embedding for Anchor Link Prediction with Social Adversarial Attacks
Recommendations
Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction
KDD '20: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data MiningCross-platform account matching plays a significant role in social network analytics, and is beneficial for a wide range of applications. However, existing methods either heavily rely on high-quality user generated content (including user profiles) or ...
Anchor Link Prediction in Online Social Network Using Graph Embedding and Binary Classification
Computational Collective IntelligenceAbstractWith the widespread popularity as well as the variety of different online social networks. Today, each user can join many social networks at the same time for many different purposes. They can join Facebook to share and update status, join ...
Clustered embedding of massive social networks
SIGMETRICS '12: Proceedings of the 12th ACM SIGMETRICS/PERFORMANCE joint international conference on Measurement and Modeling of Computer SystemsThe explosive growth of social networks has created numerous exciting research opportunities. A central concept in the analysis of social networks is a proximity measure, which captures the closeness or similarity between nodes in the network. Despite ...






Comments