MSGCN: Multi-Subgraph Based Heterogeneous Graph Convolution Network Embedding
Source abstract
Abstract
Heterogeneous graph embedding has become a hot topic in network embedding in recent years and has been widely used in lots of practical scenarios. However, most of the existing heterogeneous graph embedding methods cannot make full use of all the auxiliary information. So we proposed a new method called Multi-Subgraph based Graph Convolution Network (MSGCN), which uses topology information, semantic information, and node feature information to learn node embedding vector. In MSGCN, the graph is firstly decomposed into multiple subgraphs according to the type of edges. Then convolution operation is adopted for each subgraph to obtain the node representations of each subgraph. Finally, the node representations are obtained by aggregating the representation vectors of nodes in each subgraph. Furthermore, we discussed the application of MSGCN with respect to a transductive learning task and inductive learning task, respectively. A node sampling method for inductive learning tasks to obtain representations of new nodes is proposed. This sampling method uses the attention mechanism to find important nodes and then assigns different weights to different nodes during aggregation. We conducted an experiment on three datasets. The experimental results indicate that our MSGCN outperforms the state-of-the-art methods in multi-class node classification tasks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Complex Network Analysis Techniques · Recommender Systems and Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science, Sichuan University, Chengdu 610065, China
Funding
the Sichuan Science and Technology Program
References (46)
Show source-provided references
1. Hamilton, W.L., Ying, R., and Leskovec, J. (2017). Representation learning on graphs: Methods and applications. arXiv.
2. Yi, P., Huang, F., and Peng, J. (May, January 29). A Fine-grained Graph-based Spatiotemporal Network for Bike Flow Prediction in Bike-sharing Systems. Proceedings of the 2021 SIAM International Conference on Data Mining (SDM), Virtual.10.1137/1.9781611976700.58 ↗
3. 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, KDD ’14, New York, NY, USA.10.1145/2623330.2623732 ↗
4. Grover, A., and Leskovec, J. (2016, January 13–17). node2vec: Scalable feature learning for networks. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939754 ↗
5. 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, WWW 2015, Florence, Italy.10.1145/2736277.2741093 ↗
6. Hamilton, W.L., Ying, Z., and Leskovec, J. (2017, January 4–9). Inductive representation learning on large graphs. Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA.
7. Kipf, T.N., and Welling, M. (2017, January 24–26). Semi-supervised classification with graph convolutional networks. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017, Toulon, France.
8. Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (May, January 30). Graph attention networks. Proceedings of the 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada.
9. Dong, Y., Hu, Z., Wang, K., Sun, Y., and Tang, J. (2020, January 11–17). Heterogeneous network representation learning. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, Yokohama, Japan.10.24963/ijcai.2020/677 ↗
10. A survey of heterogeneous information network analysis10.1109/TKDE.2016.2598561 ↗
11. Cen, Y., Zou, X., Zhang, J., Yang, H., Zhou, J., and Tang, J. (2019, January 4–8). Representation learning for attributed multiplex heterogeneous network. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA.10.1145/3292500.3330964 ↗
12. 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 World Wide Web Conference, WWW 2019, San Francisco, CA, USA.10.1145/3308558.3313562 ↗
13. Heterogeneous information network embedding for recommendation10.1109/TKDE.2018.2833443 ↗
14. 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 & Data Mining, KDD 2019, Anchorage, AK, USA,.10.1145/3292500.3330961 ↗
15. Hu, Z., Dong, Y., Wang, K., and Sun, Y. (2020, January 20–24). Heterogeneous graph transformer. Proceedings of the WWW ’20: The Web Conference 2020, Taipei, Taiwan.10.1145/3366423.3380027 ↗
16. Fu, T.-Y., Lee, W.-C., and Lei, Z. (2017, January 6–10). Hin2vec: Explore meta-paths in heterogeneous information networks for representation learning. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, CIKM 2017, Singapore.10.1145/3132847.3132953 ↗
17. Zhao, J., Wang, X., Shi, C., Hu, B., Song, G., and Ye, Y. (2021, January 2–9). Heterogeneous graph structure learning for graph neural networks. Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event.
18. 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 KDD ’21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, Singapore.10.1145/3447548.3467415 ↗
19. Adhikari, B., Zhang, Y., Ramakrishnan, N., and Prakash, B.A. (2017, January 18–21). Distributed representations of subgraphs. Proceedings of the 2017 IEEE International Conference on Data Mining Workshops (ICDMW), New Orleans, LA, USA.10.1109/ICDMW.2017.20 ↗
20. Yuan, C., Li, J., Zhou, W., Lu, Y., Zhang, X., and Hu, S. (2020, January 14–18). Dyhgcn: A dynamic heterogeneous graph convolutional network to learn users’ dynamic preferences for information diffusion prediction. Proceedings of the Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2020, Ghent, Belgium.10.1007/978-3-030-67664-3_21 ↗
21. Cao, S., Lu, W., and Xu, Q. (2015, January 19–23). Grarep: Learning graph representations with global structural information. Proceedings of the Proceedings of the 24th ACM International Conference on Information and Knowledge Management, CIKM 2015, Melbourne, VIC, Australia.10.1145/2806416.2806512 ↗
22. Ou, M., Cui, P., Pei, J., Zhang, Z., and Zhu, W. (2016, January 13–17). Asymmetric transitivity preserving graph embedding. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939751 ↗
23. 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 ↗
24. 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 ↗
25. Adhikari, B., Zhang, Y., Ramakrishnan, N., and Prakash, B.A. (2018). Sub2vec: Feature learning for subgraphs. Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer.10.1007/978-3-319-93037-4_14 ↗
26. Narayanan, A., Chandramohan, M., Chen, L., Liu, Y., and Saminathan, S. (2016). subgraph2vec: Learning distributed representations of rooted sub-graphs from large graphs. arXiv.
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 1th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia.10.1145/2783258.2783307 ↗
28. Wang, M., Lin, Y., Lin, G., Yang, K., and Wu, X. (2020, January 23–27). M2GRL: A multi-task multi-view graph representation learning framework for web-scale recommender systems. Proceedings of the KDD ’20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Virtual Event, CA, USA.10.1145/3394486.3403284 ↗
29. Mahdavi, S., Khoshraftar, S., and An, A. (2018, January 10–13). dynnode2vec: Scalable dynamic network embedding. Proceedings of the International Conference on Big Data, Big Data 2018, Seattle, WA, USA.10.1109/BigData.2018.8621910 ↗
30. Pareja, A., Domeniconi, G., Chen, J., Ma, T., Suzumura, T., Kanezashi, H., Kaler, T., Schardl, T.B., and Leiserson, C.E. (2020, January 7–12). Evolvegcn: Evolving graph convolutional networks for dynamic graphs. Proceedings of the The Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2020, The Thirty-Second Innovative Applications of Artificial Intelligence Conference, IAAI 2020, The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2020, New York, NY, USA.
31. Nguyen, G.H., Lee, J.B., Rossi, R.A., Ahmed, N.K., Koh, E., and Kim, S. (2018, January 23–27). Continuous-time dynamic network embeddings. Proceedings of the Companion of the The Web Conference 2018 on The Web Conference 2018, WWW 2018, Lyon, France.10.1145/3184558.3191526 ↗
32. Ye, Y., Hou, S., Chen, L., Lei, J., Wan, W., Wang, J., Xiong, Q., and Shao, F. (2019, January 10–16). Out-of-sample node representation learning for heterogeneous graph in real-time android malware detection. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China.10.24963/ijcai.2019/576 ↗
33. Sankar, A., Wu, Y., Gou, L., Zhang, W., and Yang, H. (2020, January 3–7). Dysat: Deep neural representation learning on dynamic graphs via self-attention networks. Proceedings of the WSDM ’20: The Thirteenth ACM International Conference on Web Search and Data Mining, Houston, TX, USA.10.1145/3336191.3371845 ↗
34. Collective classification in network data
35. Wang, X., Cui, P., Wang, J., Pei, J., Zhu, W., and Yang, S. (2017, January 4–9). Community preserving network embedding. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence.10.1609/aaai.v31i1.10488 ↗
36. Graph embedding techniques, applications, and performance: A survey10.1016/j.knosys.2018.03.022 ↗
37. Ahmed, A., Shervashidze, N., Narayanamurthy, S.M., Josifovski, V., and Smola, A.J. (2013, January 13–17). Distributed large-scale natural graph factorization. Proceedings of the 22nd International World Wide Web Conference, WWW ’13, Rio de Janeiro, Brazil.10.1145/2488388.2488393 ↗
38. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013, January 2–4). Efficient estimation of word representations in vector space. Proceedings of the 1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA.
39. 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 WWW ’20: The Web Conference 2020, Taipei, Taiwan.10.1145/3366423.3380297 ↗
40. Le, Q.V., and Mikolov, T. (2014, January 21–26). Distributed representations of sentences and documents. Proceedings of the 31th International Conference on Machine Learning, ICML 2014, Beijing, China.
41. Xie, Y., Li, C., Yu, B., Zhang, C., and Tang, Z. (2020). A survey on dynamic network embedding. arXiv.
42. Rong, X. (2014). word2vec parameter learning explained. arXiv.
43. Yang, S., Song, G., Jin, Y., and Du, L. (2020, January 11–17). Domain adaptive classification on heterogeneous information networks. Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, Yokohama, Japan.10.24963/ijcai.2020/196 ↗
44. Kong, X., Yu, P.S., Ding, Y., and Wild, D.J. (November, January 29). Meta path-based collective classification in heterogeneous information networks. Proceedings of the 21st ACM International Conference on Information and Knowledge Management, CIKM’12, Maui, HI, USA.
45. Du, J., Zhang, S., Wu, G., Moura, J.M.F., and Kar, S. (2017). Topology adaptive graph convolutional networks. arXiv.
46. Graphinception: Convolutional neural networks for collective classification in heterogeneous information networks