JARUA: Joint Embedding of Attributes and Relations for User Alignment across Social Networks
Source abstract
Abstract
User alignment (UA), a central issue for social network analysis, aims to recognize the same natural persons across different social networks. Existing studies mainly focus on the positive effects of incorporating user attributes and network structure on UA. However, there have been few in-depth studies into the existing challenges for the joint integration of different types of text attributes, the imbalance between user attributes and network structure, and the utilization of massive unidentified users. To this end, this paper presents a high-accuracy embedding model named Joint embedding of Attributes and Relations for User Alignment (JARUA), to tackle the UA problem. First, a mechanism that can automatically identify the granularity of user attributes is introduced for handling multi-type user attributes. Second, a graph attention network is employed to extract the structural features and is integrated with user attributes features. Finally, an iterative training algorithm with quality filters is introduced to bootstrap the model performances. We evaluate JARUA on two real-world data sets. Experimental results demonstrate the superiority of the proposed method over several state-of-the-art approaches.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Recommender Systems and Techniques · Complex Network Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer and Software Engineering, Xihua University, Chengdu 610039, China
Funding
Science and Technology Program of Sichuan Province · National Natural Science Foundation of China
References (54)
Show source-provided references
1. User Identity Linkage across Online Social Networks: A Review10.1145/3068777.3068781 ↗
2. Social Friend Recommendation Based on Multiple Network Correlation10.1109/TMM.2015.2510333 ↗
3. Zhang, J., Yu, P.S., and Zhou, Z.H. (2014, January 24–27). Meta-path based multi-network collective link prediction. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623645 ↗
4. Zafarani, R., and Liu, H. (2014, January 1–4). Users joining multiple sites: Distributions and patterns. Proceedings of the 8th International Conference on Weblogs and Social Media, Ann Arbor, MI, USA.10.1609/icwsm.v8i1.14564 ↗
5. Users joining multiple sites: Friendship and popularity variations across sites10.1016/j.inffus.2015.07.002 ↗
6. Zhang, J., Chen, B., Wang, X., Song, G., Chen, H., Li, C., Jin, F., and Zhang, Y. (2018, January 22–26). MEgo2Vec: Embedding matched ego networks for user alignment across social networks. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.10.1145/3269206.3271705 ↗
7. MAUIL: Multi-level attribute embedding for semi-supervised user identity linkage10.1016/j.ins.2022.02.023 ↗
8. Malhotra, A., Totti, L., Meira, W., Kumaraguru, P., and Almeida, V. (2012, January 26–29). Studying User Footprints in Different Online Social Networks. Proceedings of the International Conference on Advances in Social Networks Analysis and Mining, Istanbul, Turkey.10.1109/ASONAM.2012.184 ↗
9. Acquisti, A., Gross, R., and Stutzman, F. (2014). Face Recognition and Privacy in the Age of Augmented Reality. J. Priv. Confid., 6.10.29012/jpc.v6i2.638 ↗
10. Feng, J., Zhang, M., Wang, H., Yang, Z., Zhang, C., Li, Y., and Jin, D. (2019, January 13–17). DPlink: User identity linkage via deep neural network from heterogeneous mobility data. Proceedings of the World Wide Web Conference, San Francisco, CA, USA.10.1145/3308558.3313424 ↗
11. Zhang, J., Kong, X., and Yu, P.S. (2014, January 24–28). Transferring Heterogeneous Links across Location-Based Social Networks. Proceedings of the 7th ACM international Conference on Web Search and Data Mining, New York, NY, USA.10.1145/2556195.2559894 ↗
12. User Identity Linkage Across Social Media via Attentive Time-Aware User Modeling10.1109/TMM.2020.3034540 ↗
13. Heimann, M., Safavi, T., Shen, H., and Koutra, D. (2018, January 22–26). REGAL: Representation Learning-based Graph Alignment. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.10.1145/3269206.3271788 ↗
14. Social network alignment: A bi-layer graph attention neural networks based method10.1007/s10489-022-03216-w ↗
15. Zhong, Z., Cao, Y., Guo, M., and Nie, Z. (2018, January 2–7). CoLink: An unsupervised framework for user identity linkage. Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.12014 ↗
16. Zhang, Y., Tang, J., Yang, Z., Pei, J., and Yu, P.S. (2015, January 10–13). COSNET: Connecting Heterogeneous Social Networks with Local and Global Consistency. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia.10.1145/2783258.2783268 ↗
17. Velikovi, P., Casanova, A., Lio, P., Cucurull, G., Romero, A., and Bengio, Y. (May, January 30). Graph attention networks. Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada.
18. Zafaranl, R., and Liu, H. (2009, January 17–20). Connecting Corresponding Identities across Communitie. Proceedings of the 3rd International Conference on Weblogs and Social Media, San Jose, CA, USA.10.1609/icwsm.v3i1.13993 ↗
19. Vosecky, J., Hong, D., and Shen, V.Y. (2009, January 28–31). User identification across multiple social networks. Proceedings of the 1st International Conference on Networked Digital Technologies, Ostrava, Czech Republic.10.1109/NDT.2009.5272173 ↗
20. Kong, X., Zhang, J., and Yu, P.S. (November, January 27). Inferring anchor links across multiple heterogeneous social networks. Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, San Francisco, CA, USA.
21. Iofciu, T., Fankhauser, P., Abel, F., and Bischoff, K. (2011, January 17–21). Identifying Users Across Social Tagging Systems. Proceedings of the 5th International Conference on Weblogs and Social Media, Barcelona, Spain.
22. Man, T., Shen, H., Liu, S., Jin, X., and Cheng, X. (2016, January 9–15). Predict anchor links across social networks via an embedding approach. Proceedings of the 25th International Joint Conference on Artificial Intelligence, New York, NY, USA.
23. Mu, X., Zhu, F., Lim, E.P., Xiao, J., Wang, J., and Zhou, Z.H. (2016, January 13–17). User identity linkage by latent user space modelling. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939849 ↗
24. Structured Learning from Heterogeneous Behavior for Social Identity Linkage10.1109/TKDE.2015.2397434 ↗
25. ABNE: An Attention-Based Network Embedding for User Alignment Across Social Networks10.1109/ACCESS.2019.2900095 ↗
26. Siamese Neural Networks for User Identity Linkage Through Web Browsing10.1109/TNNLS.2019.2929575 ↗
27. Exploiting similarities of user friendship networks across social networks for user identification10.1016/j.ins.2019.08.022 ↗
28. Deep multi-granularity graph embedding for user identity linkage across social networks10.1016/j.knosys.2019.105301 ↗
29. RLINK: Deep reinforcement learning for user identity linkage10.1007/s11280-020-00833-8 ↗
30. Liu, J., Zhang, F., Song, X., Song, Y.I., Lin, C.Y., and Hon, H.W. (2013, January 4–8). What’s in a name? An unsupervised approach to link users across communities. Proceedings of the 6th ACM International Conference on Web Search and Data Mining, Rome, Italy.10.1145/2433396.2433457 ↗
31. Li, C., Wang, S., Yu, P.S., Zheng, L., Zhang, X., Li, Z., and Liang, Y. (2018, January 22–26). Distribution distance minimization for unsupervised user identity linkage. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Italy.10.1145/3269206.3271675 ↗
32. Lacoste-Julien, S., Palla, K., Davies, A., Kasneci, G., Graepel, T., and Ghahramani, Z. (2013, January 11–14). SiGMa: Simple greedy matching for aligning large knowledge bases. Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Chicago, IL, USA.
33. Identifying users across social networks based on dynamic core interests10.1016/j.neucom.2015.10.147 ↗
34. Riederer, C., Kim, Y., Chaintreau, A., Korula, N., and Lattanzi, S. (2016, January 11–15). Linking Users Across Domains with Location Data: Theory and Validation. Proceedings of the 25th International Conference on World Wide Web, Montréal, QC, Canada.10.1145/2872427.2883002 ↗
35. Structure Based User Identification across Social Networks10.1109/TKDE.2017.2784430 ↗
36. Zhou, F., Wen, Z.J., Zhong, T., Trajcevski, G., Xu, X., and Liu, L.Y. (2020, January 7–11). Unsupervised User Identity Linkage via Graph Neural Networks. Proceedings of the 2020 IEEE Global Communications Conference (GLOBECOM 2020), Taipei, Taiwan.10.1109/GLOBECOM42002.2020.9322311 ↗
37. Matching user accounts with spatio-temporal awareness across social networks10.1016/j.ins.2021.04.030 ↗
38. Liu, L., Cheung, W.K., Li, X., and Liao, L. (2016, January 9–15). Aligning users across social networks using network embedding. Proceedings of the 25th International Joint Conference on Artificial Intelligence, New York, NY, USA.
39. Tan, S., Guan, Z., Cai, D., Qin, X., Bu, J., and Chen, C. (2014, January 27–31). Mapping users across networks by manifold alignment on hypergraph. Proceedings of the 28th AAAI Conference on Artificial Intelligence, Québec, QC, Canada.10.1609/aaai.v28i1.8720 ↗
40. Cross-Platform Identification of Anonymous Identical Users in Multiple Social Media Networks10.1109/TKDE.2015.2485222 ↗
41. Learning to Map Social Network Users by Unified Manifold Alignment on Hypergraph10.1109/TNNLS.2018.2812888 ↗
42. Li, C., Wang, S., Wang, Y., Yu, P., Liang, Y., Liu, Y., and Li, Z. (February, January 27). Adversarial Learning for Weakly-Supervised Social Network Alignment. Proceedings of the 33nd AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.10.1609/aaai.v33i01.3301996 ↗
43. Li, C., Wang, S., Wang, H., Liang, Y., Yu, P.S., Li, Z., and Wang, W. (2019, January 3–7). Partially shared adversarial learning for semi-supervised multi-platform user identity linkage. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, China.10.1145/3357384.3357904 ↗
44. Structural Representation Learning for User Alignment Across Social Networks
45. MFRep: Joint user and employer alignment across heterogeneous social networks10.1016/j.neucom.2020.07.013 ↗
46. Estimating the Selectivity of tf-idf based Cosine Similarity Predicates10.1145/1328854.1328855 ↗
47. Finding Structure with Randomness: Probabilistic Algorithms for Constructing Approximate Matrix Decompositions10.1137/090771806 ↗
48. Mao, X., Wang, W., Xu, H., Lan, M., and Wu, Y. (2020, January 3–7). MRAEA: An Efficient and Robust Entity Alignment Approach for Cross-lingual Knowledge Graph. Proceedings of the 13th International Conference on Web Search and Data Mining, Houston, TX, USA.10.1145/3336191.3371804 ↗
49. Kingma, D.P., and Ba, J.L. (2015, January 7–9). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, San Diego, CA, USA.
50. Yang, C., Liu, Z., Zhao, D., Sun, M., and Chang, E.Y. (2015, January 25–31). Network Representation Learning with Rich Text Information. Proceedings of the 24th International Joint Conference on Artificial Intelligence, Buenos Aires, Argentina.
51. Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. (2015, January 18–22). LINE: Large-scale Information Network Embedding. Proceedings of the 24th International Conference on World Wide Web, Florence, Italy.10.1145/2736277.2741093 ↗
52. Cross-Network Skip-Gram Embedding for Joint Network Alignment and Link Prediction10.1109/TKDE.2020.2997861 ↗
53. Park, J.D., Tran, C., Shin, W.Y., and Cao, X. (March, January 22). Grad-Align: Gradual Network Alignment via Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, virtually.
54. Park, J.D., Tran, C., Shin, W.Y., and Cao, X. (2022, January 17–21). Grad-Align+: Empowering Gradual Network Alignment Using Attribute Augmentation. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA. CIKM 2022.10.1145/3511808.3557605 ↗