ABSTRACT
User entity alignment is the core technology of associating multisource user identities and constructing user portraits, which is of great significance in cyberspace security, personalized service recommendation, social network, data mining, and other fields. It is difficult to accurately align user entities based on common attributes when the common attributes of multisource user data are sparse. Aiming at the above problem, we propose a user entity alignment method based on cross-attribute knowledge association. Firstly, the attribute values in the user information are linked to the corresponding entities in a knowledge graph, and the representation vector of each attribute value is obtained by embedding the subgraph of the knowledge graph. With the help of knowledge graph, the knowledge association between attribute values is embedded into the attribute vectors. At the same time, to accurately measure the attribute weight, the attribute identification degree is calculated by the distribution of attribute values. Finally, the user representation vector is generated by weighted cumulative attribute value vectors, and the similarity between user vectors is calculated to judge whether two users refer to the same person entity. Experimental results demonstrate that, the accuracy, recall, and F1 score of the proposed method are not less than 0.87 on the person entity dataset with sparse attributes. Compared with existing typical methods based on common attributes and methods based on knowledge graph embedding, the accuracy, recall, and F1 score are 12%, 7% and 10% higher than the comparative algorithm respectively.
- Zafarani R, Liu H. "Connecting users across social media sites: a behavioral-modeling approach," Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago: ACM Press, 2013: 41-49.Google Scholar
- Zhang Y, Tang J, Yang Z "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: ACM Press, 2015: 1485-1494.Google Scholar
- Korula N, Lattanzi S. "An efficient reconciliation algorithm for social networks," Proceedings of the VLDB Endowment, 2014, 7(5): 377-388.Google ScholarDigital Library
- Lu C T, Shuai H H, Yu P S. "Identifying your customers in social networks," Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. Shanghai: ACM Press, 2014:391-400.Google Scholar
- Zafarani R, Liu H. "Connecting Corresponding Identities across Communities," ICWSM. 2009, 9: 354–357.Google ScholarCross Ref
- Iofciu T, Fankhauser P, Abel F "Identifying Users Across Social Tagging Systems," In International Conference on Weblogs and Social Media, Barcelona, Catalonia, Spain, July. 2010Google Scholar
- Ikeda M, Ono S, Sato I "Person Name Disambiguation on the Web by Two-Stage Clustering," In 2nd Web People Search Evaluation Workshop (WePS 2009), 18th WWW Conference.Google Scholar
- Motoyama M, Varghese G. "I seek you: searching and matching individuals in social networks," In Eleventh International Workshop on Web Information and Data Management. 2009: 67–75.Google Scholar
- Jain P, Kumaraguru P, Joshi A. "identifying users across multiple online social networks," 2013: 1259–1268.Google Scholar
- Raad E, Chbeir R, Dipanda A. "User Profile Matching in Social Networks," In International Conference on Network-Based Information Systems. 2010: 297–304.Google Scholar
- Ma J, Qiao Y, Hu G "Balancing User Profile and Social Network Structure for Anchor Link Inferring across Multiple Online Social Networks," IEEE Access. 2017, PP (99): 1-1.Google Scholar
- Wei Y C, Lin M S et al. "Name Disambiguation in Person Information Mining," IEEE/WIC/ACM International Conference on Web, 2008:378-381Google Scholar
- Wang X, Sun A, Kardes H, "Probabilistic estimates of attribute statistics and match likelihood for people entity resolution," IEEE International Conference on Big Data. IEEE, 2015.Google Scholar
- Guan S, Jin X, Jia Y "Self-learning and embedding based entity alignment," IEEE International Conference on Big Knowledge. 2017.Google Scholar
- Qiu Q, Luo J, Yin M. "Person Name Disambiguation by distinguishing the Importance of features based on Topological Distance," Current Trends in Computer Science and Mechanical Automation Vol.1. De Gruyter Open Poland, 2018, pp. 342-351.Google Scholar
- Zhang Y, Wang L, Li X "Social Identity Link Across Incomplete Social In-formation Sources Using Anchor Link Expansion," In PAKDD 2016. 2016:395–408.Google Scholar
- Goga O, Loiseau P, Sommer R "On the Reliability of Profile Matching Across Large Online Social Networks," In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2015: 1799–1808.Google Scholar
- Zhang Y, Tang J, Yang Z "Cosnet: connecting heterogeneous social networks with local and global consistency," In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2015: 1485–1494.Google Scholar
- Zhang Q, Sun Z, Hu W, "Multi-view Knowledge Graph Embedding for Entity Alignment," arXiv preprint arXiv:1906.02390, 2019.Google Scholar
- Suchanek F M, Abiteboul S, Senellart P. "PARIS: probabilistic alignment of relations, instances, and schema," Proceedings of the Vldb Endowment, 2011, 5(3):157-168.Google ScholarDigital Library
- Lee S, Hwang S. "ARIA: asymmetry resistant instance alignment," Twenty-Eighth AAAI Conference on Artificial Intelligence. 2014.Google Scholar
- Zhuang Y, Li G L, Feng J H. "Review of Knowledge base entity alignment techniques," Journal of Computer Research and Development, 2016, a53(1):165-192.Google Scholar
- Fan F, Li Z, Wang Y. "Cohesion based attribute value matching," International Congress on Image & Signal Processing. 2018.Google Scholar
- Wang X, Sun A, Kardes H "Probabilistic estimates of attribute statistics and match likelihood for people entity resolution," IEEE International Conference on Big Data. IEEE, 2015Google Scholar
- Li J, Wang Z, Zhang X "Large scale instance matching via multiple indexes and candidate selection," Knowledge-Based Systems, 2013, 50(Complete):112-120.Google ScholarDigital Library
- Wick M, Singh S, Mccallum A. "A discriminative hierarchical model for fast coreference at large scale," Proc Acl, 2012:379-388Google Scholar
- Guan S, Jin X, Jia Y "Self-learning and embedding based entity alignment," IEEE International Conference on Big Knowledge. 2017.Google Scholar
- Wu G, Ying H, Hu X. "Entity linking: an issue to extract corresponding entity with knowledge base," IEEE Access, 2018, 6(99):1-1.Google Scholar
- McNeill N, Kardes H, Borthwick A. "Dynamic record blocking: efficient linking of massive databases in mapreduce," Proceedings of the 10th International Workshop on Quality in Databases (QDB). 2012.Google Scholar
- Xu C "Research on Markov logic networks," Journal of software, 2011, 22 (8): 1699-1713Google ScholarCross Ref
- Wang X, Liu K, He S "Multi-Source Knowledge Bases Entity Alignment by Leveraging Semantic Tags," Journal of computer science, 2017 (03): 169-179Google Scholar
- Gao S, Xing Z, Ma Y "Enhancing knowledge sharing in stack overflow via automatic external web resources linking," International Conference on Engineering of Complex Computer Systems. 2018.Google Scholar
- Lacoste-Julien S, Palla K, Davies A "Sigma: Simple greedy matching for aligning large knowledge bases," Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2013: 572-580.Google Scholar
- Christen P. "Development and user experiences of an open source data cleaning, deduplication and record linkage system," ACM SIGKDD Explorations Newsletter, 2009, 11(1): 39-48Google ScholarDigital Library
- Zhao D, Ning Z, Ming X "An Improved User Identification Method Across Social Networks Via Tagging Behaviors," 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2018.Google Scholar
- Tang R, Miao Z, Jiang S "Interlayer link prediction in multiplex social networks based on multiple types of consistency between embedding vectors," IEEE Transactions on Cybernetics, 2021.Google Scholar
- Majeed A, Lee S. "Anonymization techniques for privacy preserving data publishing: A comprehensive survey," IEEE access, 2020, 9: 8512-8545.Google ScholarCross Ref
- Tang R, Jiang S, Chen X "Interlayer link prediction in multiplex social networks: an iterative degree penalty algorithm," Knowledge-Based Systems, 2020, 194: 105598.Google ScholarCross Ref
- Milne D, Witten I H. "Learning to link with wikipedia,"Proceedings of the 17th ACM conference on Information and knowledge management. ACM, 2008: 509-518.Google Scholar
- Shen W, Wang J, Han J. "Entity linking with a knowledge base: issues, techniques, and solutions," IEEE Transactions on Knowledge and Data Engineering, 2015, 27(2):443-460.Google ScholarCross Ref
- Zhang C, Miao Z, Xiao H "Knowledge graph embedding for hyper-relational data," Tsinghua Science & Technology, 2017, 22(2):185-197.Google ScholarCross Ref
- Bordes A, Usunier N, Garcia-Duran A "Translating embeddings for modeling multi-relational data," Advances in neural information processing systems. 2013: 2787-2795.Google Scholar
Index Terms
- User entity alignment method based on cross-attribute knowledge association
Recommendations
Cross-lingual knowledge graph entity alignment based on relation awareness and attribute involvement
AbstractEntity alignment is an effective means of matching entities from various knowledge graphs (KGs) that represent the equivalent real-world object. With the development of representation learning, recent entity alignment methods learn entity ...
Entity Attribute Alignment Method Based On Attribute Value Distribution
ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern RecognitionEntity attribute alignment aims to establish correspondence between entity attributes with the same meaning for entities belonging to the same category. It is a crucial foundational technology to construct knowledge graphs based on multi-source ...
NovEA: A Novel Model of Entity Alignment Using Attribute Triples and Relation Triples
Knowledge Science, Engineering and ManagementAbstractEntity alignment is the foundation of knowledge fusion, which can find the alignment relationships between entities in heterogeneous knowledge graphs. However, traditional methods rely on external information and need to construct data features ...
Comments