Abstract
Link prediction has received increased attention in social network analysis. One of the unique challenges in heterogeneous social networks is link prediction in new link types without verified link information, such as recommending products to new overseas groups. Existing link prediction models tend to learn type-specific knowledge on specific link types and predict missing or future links on the same link types. However, because of the uncertainty of new link types in the evolving process of social networks, it is difficult to collect sufficient verified link information in new link types. Therefore, we propose the Transferable Domain Adversarial Network (TDAN) based on transfer learning to handle the challenge. TDAN exploits transferable type-shared knowledge in historical link types to help predict the unobserved links in new link types. TDAN mainly comprises a structural encoder, a domain discriminator, and an optimization decoder. The structural encoder learns the link representations in a heterogeneous social network. Subsequently, to learn transferable type-shared knowledge, the domain discriminator distinguishes link representations into different link types while minimizing the differences between type-specific knowledge in adversarial training. Inspired by the denoising auto-encoder, the optimization decoder reconstructs the learned type-shared knowledge to eliminate the noise generated during the adversarial training. Extensive experiments on Facebook and YouTube show that TDAN can outperform the state-of-the-art models.
- [1] . 2014. An optimization framework for combining ensembles of classifiers and clusterers with applications to nontransductive semisupervised learning and transfer learning. ACM Transactions on Knowledge Discovery from Data (TKDD) 9, 1 (2014), 1–35.Google ScholarDigital Library
- [2] . 2003. Friends and neighbors on the web. Social Networks 25, 3 (2003), 211–230.Google ScholarCross Ref
- [3] . 2020. Missing link prediction using common neighbor and centrality based parameterized algorithm. Scientific Reports 10, 1 (2020), 1–9.Google Scholar
- [4] . 2019. A gravitation-based link prediction approach in social networks. Swarm and Evolutionary Computation 44 (2019), 176–186.Google ScholarCross Ref
- [5] . 2016. Directed networks’ different link formation mechanisms causing degree distribution distinction. Physica A: Statistical Mechanics and its Applications 462 (2016), 479–491.Google ScholarCross Ref
- [6] . 2010. Transfer learning for collective link prediction in multiple heterogenous domains. In ICML.Google Scholar
- [7] . 2019. Representation learning for attributed multiplex heterogeneous network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1358–1368.Google ScholarDigital Library
- [8] , Jing Zhang, Xiaokang Zhang, Xiaobin Tang, Lingfan Cai, Hong Chen, Cuiping Li, Peng Zhang, Jie Tang. 2022. CODE: Contrastive pre-training with adversarial fine-tuning for zero-shot expert linking. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 11846–11854.Google ScholarCross Ref
- [9] . 2018. PME: Projected metric embedding on heterogeneous networks for link prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 1177–1186.Google ScholarDigital Library
- [10] . 2012. Discovering missing links in networks using vertex similarity measures. In Proceedings of the 27th Annual ACM Symposium on Applied Computing. 138–143.Google ScholarDigital Library
- [11] . 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research 12, (2011), 2493–2537.Google ScholarDigital Library
- [12] . 2018. Generative adversarial networks: An overview. IEEE Signal Processing Magazine 35, 1 (2018), 53–65.Google ScholarCross Ref
- [13] . 2022. Graph transfer learning via adversarial domain adaptation with graph convolution. IEEE Transactions on Knowledge and Data Engineering (2022).Google ScholarDigital Library
- [14] . 2021. Predicting influential users in online social network groups. ACM Transactions on Knowledge Discovery from Data (TKDD) 15, 3 (2021), 1–50.Google ScholarDigital Library
- [15] . 2017. metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 135–144.Google ScholarDigital Library
- [16] . 2016. Domain-adversarial training of neural networks. The Journal of Machine Learning Research 17, 1 (2016), 2096–2030.Google ScholarCross Ref
- [17] . 2020. Accelerating large-scale heterogeneous interaction graph embedding learning via importance sampling. ACM Transactions on Knowledge Discovery from Data (TKDD) 15, 1 (2020), 1–23.Google ScholarDigital Library
- [18] . 2014. A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188 (2014).Google Scholar
- [19] . 2010. Cold start link prediction. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 393–402.Google ScholarDigital Library
- [20] . 2016. An intelligent movie recommendation system through group-level sentiment analysis in microblogs. Neurocomputing 210 (2016), 164–173.Google ScholarDigital Library
- [21] . 2020. Friend recommendation for cross marketing in online brand community based on intelligent attention allocation link prediction algorithm. Expert Systems with Applications 139 (2020), 112839.Google ScholarDigital Library
- [22] . 2007. The link-prediction problem for social networks. Journal of the American Society for Information Science and Technology 58, 7 (2007), 1019–1031.Google ScholarCross Ref
- [23] . 2010. New perspectives and methods in link prediction. In Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 243–252.Google ScholarDigital Library
- [24] . 2013. Deep learning approaches for link prediction in social network services. In International Conference on Neural Information Processing. Springer, 425–432.Google ScholarDigital Library
- [25] . 2021. Jointly modeling heterogeneous student behaviors and interactions among multiple prediction tasks. ACM Transactions on Knowledge Discovery from Data (TKDD) 16, 1 (2021), 1–24.Google Scholar
- [26] . 2011. Link prediction in complex networks: A survey. Physica A: Statistical Mechanics and its Applications 390, 6 (2011), 1150–1170.Google ScholarCross Ref
- [27] . 2017. A scalable method for link prediction in large real world networks. J. Parallel and Distrib. Comput. 109 (2017), 89–101.Google ScholarCross Ref
- [28] . 2019. A comprehensive survey of edge prediction in social networks: Techniques, parameters and challenges. Expert Systems with Applications 124 (2019), 164–181.Google ScholarDigital Library
- [29] . 2021. Knowledge graph embedding for link prediction: A comparative analysis. ACM Transactions on Knowledge Discovery from Data (TKDD) 15, 2 (2021), 1–49.Google ScholarDigital Library
- [30] . 2019. Continuous-time relationship prediction in dynamic heterogeneous information networks. ACM Transactions on Knowledge Discovery from Data (TKDD) 13, 4 (2019), 1–31.Google ScholarDigital Library
- [31] . 2018. Representation learning for classification in heterogeneous graphs with application to social networks. ACM Transactions on Knowledge Discovery from Data (TKDD) 12, 5 (2018), 1–33.Google ScholarDigital Library
- [32] . 2016. A survey of heterogeneous information network analysis. IEEE Transactions on Knowledge and Data Engineering 29, 1 (2016), 17–37.Google ScholarDigital Library
- [33] . 2013. Mining heterogeneous information networks: A structural analysis approach. ACM SIGKDD Explorations Newsletter 14, 2 (2013), 20–28.Google ScholarDigital Library
- [34] . 2016. Support vector machine. In Machine Learning Models and Algorithms for Big Data Classification. Springer, 207–235.Google Scholar
- [35] . 2015. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web. 1067–1077.Google ScholarDigital Library
- [36] . 2008. ArnetMiner: Extraction and mining of academic social networks. In Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 990–998.Google ScholarDigital Library
- [37] . 2016. Complex embeddings for simple link prediction. In International Conference on Machine Learning. PMLR, 2071–2080.Google ScholarDigital Library
- [38] . 2017. Nodes’ Evolution diversity and link prediction in social networks. IEEE Transactions on Knowledge and Data Engineering 29, 10 (2017), 2263–2274.
DOI: Google ScholarDigital Library - [39] . 2021. Identifying and evaluating anomalous structural change-based nodes in generalized dynamic social networks. ACM Transactions on the Web 15, 4 (2021), 1–22.Google ScholarDigital Library
- [40] . 2021. Self-supervised learning of contextual embeddings for link prediction in heterogeneous networks. In Proceedings of the Web Conference 2021. 2946–2957.Google ScholarDigital Library
- [41] . 2015. Link prediction in social networks: The state-of-the-art. Science China Information Sciences 58, 1 (2015), 1–38.Google ScholarCross Ref
- [42] . 2014. A review of link prediction in social networks. In 2014 International Conference on Management of E-Commerce and E-Government. IEEE, 147–150.Google ScholarDigital Library
- [43] . 2019. Heterogeneous graph attention network. In The World Wide Web Conference. 2022–2032.Google ScholarDigital Library
- [44] . 2021. Con&Net: A cross-network anchor link discovery method based on embedding representation. ACM Transactions on Knowledge Discovery from Data (TKDD) 16, 2 (2021), 1–18.Google Scholar
- [45] . 2017. A balanced modularity maximization link prediction model in social networks. Information Processing & Management 53, 1 (2017), 295–307.Google ScholarCross Ref
- [46] . 2018. Link prediction in complex networks based on the interactions among paths. Physica A: Statistical Mechanics and its Applications 510 (2018), 52–67.Google ScholarCross Ref
- [47] . 2020. Taxonomy of link prediction for social network analysis: A review. IEEE Access 8 (2020), 183470–183487.
DOI: Google ScholarCross Ref - [48] . 2015. Integrated anchor and social link predictions across social networks. In Twenty-Fourth International Joint Conference on Artificial Intelligence.Google Scholar
- [49] . 2018. Link prediction based on graph neural networks. Advances in Neural Information Processing Systems 31 (2018), 5165–5175.Google Scholar
- [50] . 2018. Joint representation learning for location-based social networks with multi-grained sequential contexts. ACM Transactions on Knowledge Discovery from Data (TKDD) 12, 2 (2018), 1–21.Google ScholarDigital Library
- [51] . 2009. Predicting missing links via local information. The European Physical Journal B 71, 4 (2009), 623–630.Google ScholarCross Ref
- [52] . 2021. Transfer learning of graph neural networks with ego-graph information maximization. Advances in Neural Information Processing Systems 34 (2021), 1766–1779.Google Scholar
- [53] . 2012. Uncovering missing links with cold ends. Physica A: Statistical Mechanics and its Applications 391, 22 (2012), 5769–5778.Google ScholarCross Ref
- [54] . 2020. A comprehensive survey on transfer learning. Proc. IEEE 109, 1 (2020), 43–76.Google ScholarCross Ref
Index Terms
- TDAN: Transferable Domain Adversarial Network for Link Prediction in Heterogeneous Social Networks
Recommendations
Integrated anchor and social link predictions across multiple social networks
In recent years, various online social networks offering specific services have gained great popularity and success. To enjoy more online social services, some users can be involved in multiple social networks simultaneously. A challenging problem in ...
Meta-learning adaptation network for few-shot link prediction in heterogeneous social networks
AbstractLink prediction, which aims to predict future or missing links among nodes, is a crucial research problem in social network analysis. A unique few-shot challenge is link prediction on newly emerged link types without sufficient verification ...
Link Prediction in Heterogeneous Social Networks
CIKM '16: Proceedings of the 25th ACM International on Conference on Information and Knowledge ManagementA heterogeneous social network is characterized by multiple link types which makes the task of link prediction in such networks more involved. In the last few years collective link prediction methods have been proposed for the problem of link prediction ...
Comments