MFHE: Multi-View Fusion-Based Heterogeneous Information Network Embedding
Source abstract
Abstract
Depending on the type of information network, information network embedding is classified into homogeneous information network embedding and heterogeneous information network (HIN) embedding. Compared with the homogeneous network, HIN composition is more complex and contains richer semantics. At present, the research on homogeneous information network embedding is relatively mature. However, if the homogeneous information network model is directly applied to HIN, it will cause incomplete information extraction. It is necessary to build a specialized embedding model for HIN. Learning information network embedding based on the meta-path is an effective approach to extracting semantic information. Nevertheless, extracting HIN embedding only from a single view will cause information loss. To solve these problems, we propose a multi-view fusion-based HIN embedding model, called MFHE. MFHE includes four parts: node feature space transformation, subview information extraction, multi-view information fusion, and training. MFHE divides HIN into different subviews based on meta-paths, models the local information accurately in the subviews based on the multi-head attention mechanism, and then fuses subview information through a spatial matrix. In this paper, we consider the relationship between subviews; thus, the MFHE is applicable to complex HIN embedding. Experiments are conducted on ACM and DBLP datasets. Compared with baselines, the experimental results demonstrate that the effectiveness of MFHE and HIN embedding has been improved.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Complex Network Analysis Techniques · Advanced Computing and Algorithms
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Information Engineering, Shandong University, Weihai 264209, China
Rushan Big Data Center, Shandong University, Weihai 264500, China
Funding
National Natural Science Foundation of China
References (45)
Show source-provided references
1. Chen, H., Bryan, P., Al-Rfou, R., and Skiena, S. (2018). A Tutorial on Network Embeddings. arXiv.
2. Network Together: Node Classification via Cross-Network Deep Network Embedding10.1109/TNNLS.2020.2995483 ↗
3. DNC: A Deep Neural Network-based Clustering-oriented Network Embedding Algorithm10.1016/j.jnca.2020.102854 ↗
4. Chen, X., Kang, B., Lijffijt, J., and De Bie, T. (2021). ALPINE: Active Link Prediction Using Network Embedding. Appl. Sci., 11.10.3390/app11115043 ↗
5. High-Order Proximity Preserved Embedding for Dynamic Networks
6. Perozzi, B., Al-Rfou, R., and Skiena, S. (2014, January 24–27). DeepWalk: Online Learning of Social Representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623732 ↗
7. 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 ↗
8. Grover, A., and Leskovec, J. (2016, January 13–17). Node2vec: Scalable Feature Learning for Networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939754 ↗
9. A Unified Framework for Community Detection and Network Representation Learning10.1109/TKDE.2018.2852958 ↗
10. Chanpuriya, S., and Musco, C. (2020, January 6–10). Infinitewalk: Deep Network Embeddings as Laplacian Embeddings with A Nonlinearity. Proceedings of the the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Electr Network, Virtual Event.10.1145/3394486.3403185 ↗
11. A Scalable Attribute-Aware Network Embedding System10.1016/j.neucom.2019.01.106 ↗
12. Progresses and Challenges in Link Prediction10.1016/j.isci.2021.103217 ↗
13. Heterogeneous Social Recommendation Model With Network Embedding10.1109/ACCESS.2020.3038022 ↗
14. The Comparative Toxicogenomics Database: Update 201710.1093/nar/gkw838 ↗
15. Chen, Y., and Wang, C. (2017, January 27–30). HINE: Heterogeneous Information Network Embedding. Proceedings of the 22nd International Conference on Database Systems for Advanced Applications, Suzhou, China.10.1007/978-3-319-55753-3_12 ↗
16. Attributed Collaboration Network Embedding for Academic Relationship Mining10.1145/3409736 ↗
17. Dynamic Heterogeneous Information Network Embedding With Meta-Path Based Proximity10.1109/TKDE.2020.2993870 ↗
18. RHINE: Relation Structure-aware Heterogeneous Information Network Embedding10.1109/TKDE.2020.2982898 ↗
19. Xu, Z., Liu, H., Li, J., Zhang, Q., and Tang, Y. (2022). CKGAT: Collaborative Knowledge-Aware Graph Attention Network for Top-N Recommendation. Appl. Sci., 12.10.3390/app12031669 ↗
20. Sun, Y., Han, J., Yan, X., Yu, P.S., and Wu, T. (September, January 29). Pathsim: Meta Path-Based Top-K Similarity Search in Heterogeneous Information Network. Proceedings of the VLDB Endowment, New York, NY, USA.
21. Liang, T., and Liu, J. (2020, January 19–24). Meta-Path Generation Online for Heterogeneous Network Embedding. Proceedings of the 2020 International Joint Conference on Neural Networks, Glasgow, UK.10.1109/IJCNN48605.2020.9206882 ↗
22. Yang, Y., Guan, Z., Li, J., Zhao, W., Cui, J., and Wang, Q. (2021). Interpretable and Efficient Heterogeneous Graph Convolutional Network. IEEE Trans. Knowl. Data Eng., 1–14.10.1109/TKDE.2021.3101356 ↗
23. Yang, C., Liu, M., He, F., Zhang, X., Peng, J., and Han, J. (2019, January 13–17). Similarity Modeling on Heterogeneous Networks via Automatic Path Discovery. Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Dublin, Ireland.10.1007/978-3-030-10928-8_3 ↗
24. Hong, H., Guo, H., Lin, Y., Yang, X., Li, Z., and Ye, J. (2020, January 7–12). An Attention-Based Graph Neural Network for Heterogeneous Structural ALearning. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.
25. Hu, Z., Dong, Y., Wang, K., and Sun, Y. (2020, January 20–24). Heterogeneous Graph Transformer. Proceedings of the 29th World Wide Web Conference, New York, NY, USA.10.1145/3366423.3380027 ↗
26. Heterogeneous Information Network Embedding for Recommendation10.1109/TKDE.2018.2833443 ↗
27. Tang, J., Qu, M., and Mei, Q. (2015, January 10–13). PTE: Predictive Text Embedding through Large-Scale Heterogeneous Text Networks. Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia.10.1145/2783258.2783307 ↗
28. Wang, H., Zhang, F., Hou, M., Xie, X., Guo, M., and Liu, Q. (2018, January 5–9). Shine: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction. Proceedings of the 11th ACM International Conference on Web Search and Data Mining, Marina Del Rey, CA, USA.10.1145/3159652.3159666 ↗
29. Robust Multi-View Data Clustering with Multi-View Capped-Norm K-means10.1016/j.neucom.2018.05.072 ↗
30. MVGAN: Multi-View Graph Attention Network for Social Event Detection
31. Nonlinear Dimensionality Reduction by Locally Linear Embedding10.1126/science.290.5500.2323 ↗
32. Link Prediction Schemes Contra Weisfeiler-Leman Models
33. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013, January 2–4). Efficient Estimation of Word Representations in Vector Space. Proceedings of the International Conference on Learning Representations, Scottsdale, AZ, USA.
34. Wang, D., Cui, P., and Zhu, W. (2016, January 13–17). Structural Deep Network Embedding. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939753 ↗
35. Wang, H., Wang, J., Wang, J., Zhao, M., Zhang, W., Zhang, F., Xie, X., and Guo, M. (2018, January 2–7). GraphGAN: Graph Representation Learning with Generative Adversarial Nets. Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11872 ↗
36. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the International Conference on Learning Representations, Toulon, France.
37. Hamilton, W., Ying, Z., and Leskovec, J. (2017, January 4–9). Inductive Representation Learning on Large Graphs. Proceedings of the 31st Annual Conference on Neural Information Processing Systems, Long Beach, CA, USA.
38. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (May, January 30). Graph Attention Networks. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
39. A Survey on Heterogeneous Network Representation Learning10.1016/j.patcog.2021.107936 ↗
40. 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 ↗
41. Wang, X., Ji, H., Shi, C., Wang, B., Cui, P., Yu, P., and Ye, Y. (2019, January 13–17). Heterogeneous Graph Attention Network. Proceedings of the World Wide Web Conference, San Francisco, CA, USA.10.1145/3308558.3313562 ↗
42. Zhang, C., Song, D., Huang, C., Swami, A., and Chawla, N.V. (2019, January 4–8). Heterogeneous Graph Neural Network. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/3292500.3330961 ↗
43. Wang, X., Liu, N., Han, H., and Shi, C. (2021, January 14–18). Self-Supervised Heterogeneous Graph Neural Network with Co-contrastive Learning. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/3447548.3467415 ↗
44. Jin, D., Huo, C., Liang, C., and Yang, L. (2021, January 19–23). Heterogeneous Graph Neural Network via Attribute Completion. Proceedings of the 30th World Wide Web Conference, Electr Network, Virtual Event.10.1145/3442381.3449914 ↗
45. (2022, July 11). The Source Code of Heterogeneous Graph Attention Network. Available online: https://github.com/Jhy1993/HAN.