The Application of Lite-GRU Embedding and VAE-Augmented Heterogeneous Graph Attention Network in Friend Link Prediction for LBSNs
Source abstract
Abstract
Friend link prediction is an important issue in recommendation systems and social network analysis. In Location-Based Social Networks (LBSNs), predicting potential friend relationships faces significant challenges due to the diversity of user behaviors, along with the high dimensionality, sparsity, and complex noise in the data. To address these issues, this paper proposes a Heterogeneous Graph Attention Network (GEVEHGAN) model based on Lite Gate Recurrent Unit (Lite-GRU) embedding and Variational Autoencoder (VAE) enhancement. The model constructs a heterogeneous graph with two types of nodes and three types of edges; combines Skip-Gram and Lite-GRU to learn Point of Interest (POI) and user node embeddings; introduces VAE for dimensionality reduction and denoising of the embeddings; and employs edge-level attention mechanisms to enhance information propagation and feature aggregation. Experiments are conducted on the publicly available Foursquare dataset. The results show that the GEVEHGAN model outperforms other comparative models in evaluation metrics such as AUC, AP, and Top@K accuracy, demonstrating its superior performance in the friend link prediction task.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Complex Network Analysis Techniques · Text and Document Classification Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science, China University of Geosciences (Wuhan), Wuhan 430078, China
References (72)
Show source-provided references
1. Liben-Nowell, D., and Kleinberg, J. (2003;, January 3–8). The Link Prediction Problem for Social Networks. Proceedings of the Twelfth International Conference on Information and Knowledge Management, New Orleans, LA, USA.10.1145/956958.956972 ↗
2. Research on Precision Marketing Strategy and Personalized Recommendation Method Based on Big Data Drive10.1155/2022/6751413 ↗
3. Chen, Y.-C., Huang, H.-H., Chiu, S.-M., and Lee, C. (2021). Joint Promotion Partner Recommendation Systems Using Data from Location-Based Social Networks. ISPRS Int. J. Geo-Inf., 10.10.3390/ijgi10020057 ↗
4. The Role of the Critical Friend in Supporting and Enhancing Professional Learning and Development
5. A Review of Research on Location-Based Social Network Point of Interest Recommendation Systems
6. Clustering and Preferential Attachment in Growing Networks10.1103/PhysRevE.64.025102 ↗
7. Tong, H., Faloutsos, C., and Pan, J. (2006, January 18–22). Fast Random Walk with Restart and Its Applications. Proceedings of the Sixth International Conference on Data Mining (ICDM’06), Hong Kong, China.10.1109/ICDM.2006.70 ↗
8. Link Prediction Based on Local Random Walk10.1209/0295-5075/89/58007 ↗
9. Wang, C., Satuluri, V., and Parthasarathy, S. (2007, January 28–31). Local Probabilistic Models for Link Prediction. Proceedings of the Seventh IEEE International Conference on Data Mining (ICDM 2007), Omaha, NE, USA.10.1109/ICDM.2007.108 ↗
10. Neville, J. (2006). Statistical Models and Analysis Techniques for Learning in Relational Data, University of Massachusetts Amherst.
11. Stochastic Relational Models for Discriminative Link Prediction
12. Du, Y., Zheng, Y., Lee, K., and Zhe, S. (2018, January 17–20). Probabilistic Streaming Tensor Decomposition. Proceedings of the 2018 IEEE International Conference on Data Mining (ICDM), Sentosa, Singapore.10.1109/ICDM.2018.00025 ↗
13. Link Prediction and Path Analysis Using Markov Chains10.1016/S1389-1286(00)00044-X ↗
14. Li, X., Du, N., Li, H., Li, K., Gao, J., and Zhang, A. (2014, January 28). A Deep Learning Approach to Link Prediction in Dynamic Networks. Proceedings of the 2014 SIAM International Conference on Data Mining, Philadelphia, PA, USA.10.1137/1.9781611973440.33 ↗
15. Link Prediction through Deep Generative Model10.1016/j.isci.2020.101626 ↗
16. Wang, H., Shi, X., and Yeung, D.-Y. (March, January 25). Relational Deep Learning: A Deep Latent Variable Model for Link Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA.
17. Modeling Relational Data with Graph Convolutional Networks
18. Kipf, T.N., and Welling, M. (2016). Variational Graph Auto-Encoders 2016. arXiv.
19. The Graph Neural Network Model10.1109/TNN.2008.2005605 ↗
20. Wu, Y., Lian, D., Jin, S., and Chen, E. (2019, January 10–16). Graph Convolutional Networks on User Mobility Heterogeneous Graphs for Social Relationship Inference. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence Main Track, Macau, China.10.24963/ijcai.2019/541 ↗
21. Backes, M., Humbert, M., Pang, J., and Zhang, Y. (November, January 30). Walk2friends: Inferring Social Links from Mobility Profiles. Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, Dallas, TX, USA.10.1145/3133956.3133972 ↗
22. Social Link Inference via Multiview Matching Network from Spatiotemporal Trajectories10.1109/TNNLS.2020.2986472 ↗
23. Hamilton, W., Ying, Z., and Leskovec, J. (2017). Inductive Representation Learning on Large Graphs. Adv. Neural Inf. Process. Syst., 30.
24. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph Attention Networks. Stat, 1050.
25. Wang, X., Ji, H., Shi, C., Wang, B., Ye, Y., Cui, P., and Yu, P.S. (2019, January 13–17). Heterogeneous Graph Attention Network. Proceedings of the The World Wide Web Conference, San Francisco, CA, USA.10.1145/3308558.3313562 ↗
26. Hu, Q., Lin, W., Tang, M., and Jiang, J. (2022). Mbhan: Motif-Based Heterogeneous Graph Attention Network. Appl. Sci., 12.10.3390/app12125931 ↗
27. An Improved Context-Aware Weighted Matrix Factorization Algorithm for Point of Interest Recommendation in LBSN10.1016/j.is.2024.102366 ↗
28. Point of Interest Recommendations Based on the Anchoring Effect in Location-Based Social Network Services10.1016/j.eswa.2020.114018 ↗
29. Efficient Point-of-Interest Recommendation Services with Heterogenous Hypergraph Embedding10.1109/TSC.2022.3187038 ↗
30. Mobility Prediction on a Location-Based Social Network Using K Latest Movements of Friends10.1007/978-981-19-3394-3_33 ↗
31. Li, Y., Fan, Z., Zhang, J., Shi, D., Xu, T., Yin, D., Deng, J., and Song, X. (2022, January 17–21). Heterogeneous Hypergraph Neural Network for Friend Recommendation with Human Mobility. Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA.10.1145/3511808.3557609 ↗
32. HMGCL: Heterogeneous Multigraph Contrastive Learning for LBSN Friend Recommendation10.1007/s11280-022-01092-5 ↗
33. Yang, L., Marmolejo Duarte, C.R., and Martí Ciriquiá, P. (2021). Exploring the Applications and Limitations of Location-Based Social Network Data in Urban Spatiotemporal Analysis. [Ph.D. Thesis, Universitat Politècnica de Catalunya].
34. Using Location-Based Social Network Data for Activity Intensity Analysis10.5198/jtlu.2019.1470 ↗
35. Social Dynamics in Cities: Analysis through LBSN Data10.1016/j.procs.2022.09.143 ↗
36. Towards Multi-Dimensional Knowledge-Aware Approach for Effective Community Detection in LBSN10.1007/s11280-022-01101-7 ↗
37. POI Recommendation Method Using LSTM-Attention in LBSN Considering Privacy Protection10.1007/s40747-021-00440-8 ↗
38. Towards Privacy-Preserving Category-Aware POI Recommendation over Encrypted LBSN Data10.1016/j.ins.2024.120253 ↗
39. Sai, A.M.V.V., Zhang, K., and Li, Y. (2021, January 18–21). User Motivation Based Privacy Preservation in Location Based Social Networks. Proceedings of the 2021 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/IOP/SCI), Atlanta, GA, USA.
40. Distribution de La Flore Alpine Dans Le Bassin Des Dranses et Dans Quelques Régions Voisines
41. Friends and Neighbors on the Web10.1016/S0378-8733(03)00009-1 ↗
42. Evolution of the Social Network of Scientific Collaborations10.1016/S0378-4371(02)00736-7 ↗
43. Predicting Missing Links via Local Information10.1140/epjb/e2009-00335-8 ↗
44. Salton, G. (1983). Modern Information Retrieval, McGraw-Hill Education.
45. Similarity Index Based on Local Paths for Link Prediction of Complex Networks10.1103/PhysRevE.80.046122 ↗
46. A New Status Index Derived from Sociometric Analysis10.1007/BF02289026 ↗
47. CNDP: Link Prediction Based on Common Neighbors Degree Penalization10.1016/j.physa.2019.122950 ↗
48. A New Link Prediction Method to Alleviate the Cold-Start Problem Based on Extending Common Neighbor and Degree Centrality10.1016/j.physa.2023.128546 ↗
49. Link Prediction Using Node Information on Local Paths10.1016/j.physa.2020.124980 ↗
50. Accurate Link Prediction Method Based on Path Length between a Pair of Unlinked Nodes and Their Degree10.1007/s13278-019-0618-2 ↗
51. Kipf, T.N., and Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. arXiv.
52. He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., and Wang, M. (2020, January 25–30). LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Virtual Event, China.10.1145/3397271.3401063 ↗
53. Friend Recommendation Based on Multi-Social Graph Convolutional Network10.1109/ACCESS.2020.2977407 ↗
54. van den Berg, R., Kipf, T.N., and Welling, M. (2017). Graph Convolutional Matrix Completion 2017. arXiv.
55. Zhang, C., Song, D., Huang, C., Swami, A., and Chawla, N.V. (2019, January 25). Heterogeneous Graph Neural Network. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.10.1145/3292500.3330961 ↗
56. Dong, Y., Chawla, N.V., and Swami, A. (2017, January 13–17). Metapath2vec: Scalable Representation Learning for Heterogeneous Networks. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, NS, Canada.10.1145/3097983.3098036 ↗
57. Fu, X., Zhang, J., Meng, Z., and King, I. (2020, January 20–24). MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding. Proceedings of the Web Conference 2020, Taipei, Taiwan.10.1145/3366423.3380297 ↗
58. Fan, Y., Ju, M., Zhang, C., Zhao, L., and Ye, Y. (2021). Heterogeneous Temporal Graph Neural Network 2021. arXiv.
59. HeteroGraphRec: A Heterogeneous Graph-Based Neural Networks for Social Recommendations10.1016/j.knosys.2021.106817 ↗
60. H2Rec: Homogeneous and Heterogeneous Network Embedding Fusion for Social Recommendation10.2991/ijcis.d.210406.001 ↗
61. Yadati, N., Nimishakavi, M., Yadav, P., Nitin, V., Louis, A., and Talukdar, P. (2019). Hypergcn: A New Method for Training Graph Convolutional Networks on Hypergraphs. Adv. Neural Inf. Process. Syst., 32.
62. Dong, Y., Sawin, W., and Bengio, Y. (2020). HNHN: Hypergraph Networks with Hyperedge Neurons 2020. arXiv.
63. Feng, Y., You, H., Zhang, Z., Ji, R., and Gao, Y. (February, January 27). Hypergraph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
64. Huang, J., and Yang, J. (2021). UniGNN: A Unified Framework for Graph and Hypergraph Neural Networks 2021. arXiv.10.24963/ijcai.2021/353 ↗
65. Chien, E., Pan, C., Peng, J., and Milenkovic, O. (2022). You Are AllSet: A Multiset Function Framework for Hypergraph Neural Networks 2022. arXiv.10.1109/IJCNN55064.2022.9892328 ↗
66. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient Estimation of Word Representations in Vector Space 2013. arXiv.
67. Light Gated Recurrent Units for Speech Recognition10.1109/TETCI.2017.2762739 ↗
68. Brody, S., Alon, U., and Yahav, E. (2022). How Attentive Are Graph Attention Networks?. arXiv.
69. Li, G., Muller, M., Thabet, A., and Ghanem, B. (November, January 27). Deepgcns: Can Gcns Go as Deep as Cnns?. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
70. Li, G., Xiong, C., Thabet, A., and Ghanem, B. (2020). DeeperGCN: All You Need to Train Deeper GCNs 2020. arXiv.
71. Lv, Q., Ding, M., Liu, Q., Chen, Y., Feng, W., He, S., Zhou, C., Jiang, J., Dong, Y., and Tang, J. (2021, January 14–18). Are We Really Making Much Progress?: Revisiting, Benchmarking and Refining Heterogeneous Graph Neural Networks. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Virtual Event, Singapore.10.1145/3447548.3467350 ↗
72. Where Have You Been: Dual Spatiotemporal-Aware User Mobility Modeling for Missing Check-in POI Identification10.1016/j.ipm.2022.103030 ↗