Abstract
Most existing heterogeneous graph neural network models need more effective integration and full exploitation of features at different network levels to prevent overfitting. To address these problems, we propose an interlayer feature fusion-based heterogeneous graph neural network model, FHGN. To enhance the representation of the original input features, a residual graph attention layer is presented to aggregate neighborhood node messages and updates the central node representation. To improve the perception ability of different nodes for neighborhood information, an interlayer feature fusion layer with different strategies is designed to integrate low-order embedding and high-order semantic information adaptively. To reduce the homogeneity for node embedding, a semantic feature fusion layer is proposed to fuse the node embeddings covering semantic information learned from the different meta-path subgraphs. Experiments on several datasets show that our model outperforms the existing related works.
Similar content being viewed by others
Availability of data and materials
Link to data is included in the manuscript
References
Xie Y, Yu B, Lv S, Zhang C, Gong M (2021) A survey on heterogeneous network representation learning. Pattern Recognit 116(7:107936
Sun Y, Han J (2013) Mining heterogeneous information networks: a analysis approach. ACM SIGKDD Explorations Newsl 14(2):20–28
Wang X, Ji H, Shi C, Wang B, Ye Y, Cui P, Yu PS (2019) Heterogeneous graph attention network. In: The World Wide Web Conference, pp.2022–2032
Lu Y, Shi C, Hu L, Liu Z (2019) Relation structure-aware heterogeneous information network embedding. Proceedings of the AAAI Conference on Artificial Intelligence 33:4456–4463
Zheng Y, Hu R, Fung S-f, Yu C, Long G, Guo T, Pan S (2020) Clustering social audiences in business information networks. Pattern Recognit 100:107126. https://doi.org/10.1016/j.patcog.2019.107126
Camacho DM, Collins KM, Powers RK, Costello JC, Collins JJ (2018) Next-generation machine learning for biological networks. Cell 173(7):1581–1592. https://doi.org/10.1016/j.cell.2018.05.015
Tajeuna EG, Bouguessa M, Wang S (2018) Modeling and predicting community structure changes in time-evolving social networks. IEEE Trans Knowl Data Eng 31(6):1166–1180
Jin D, Huo C, Liang C, Yang L (2021) Heterogeneous graph neural network via attribute completion. Proceedings of the Web Conference 2021:391–400
Scarselli F, Gori M, Tsoi AC, Hagenbuchner M, Monfardini G (2008) The graph neural network model. IEEE Trans Neural Netw 20(1):61–80
Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY (2020) A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst 32(1):4–24
Fu X, Zhang J, Meng Z, King I (2020) Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. Proceedings of The Web Conference 2020:2331–2341
Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations. https://openreview.net/forum?id=SJU4ayYgl
Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR
Zhao J, Wang X, Shi C, Hu B, Song G, Ye Y (2021) Heterogeneous graph structure learning for graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence 35:4697–4705
Shao Z, Xu Y, Wei W, Wang F, Zhang Z, Zhu F (2022) Heterogeneous graph neural network with multi-view representation learning. IEEE Trans Knowl Data Eng
Lv Q, Ding M, Liu Q, Chen Y, Feng W, He S, Zhou C, Jiang J, Dong Y, Tang J (2021) Are we really making much progress? revisiting, benchmarking and refining heterogeneous graph neural networks. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 1150–1160
Hong H, Guo H, Lin Y, Yang X, Li Z, Ye J (2020) An attentionbased graph neural network for heterogeneous structural learning. Proceedings of the AAAI Conference on Artificial Intelligence 34:4132–4139
Hu Z, Dong Y, Wang K, Sun Y (2020) Heterogeneous graph transformer. Proceedings of The Web Conference 2020:2704–2710
Cui P, Wang X, Pei J, Zhu W (2018) A survey on network embedding. IEEE Trans Knowl Data Eng 31(5):833–852
Ji H, Zhu J, Wang X, Shi C, Wang B, Tan X, Li Y, He S (2021) Who you would like to share with? a study of share recommendation in social e-commerce. Proceedings of the AAAI Conference on Artificial Intelligence 35:232–239
Chen T, Zhou K, Duan K, Zheng W, Wang P, Hu X, Wang Z (2022) Bag of tricks for training deeper graph neural networks: A comprehensive benchmark study. IEEE Trans Pattern Anal Mach Intell
Wu L, Cui P, Pei J, Zhao L, Guo X (2022) Graph neural networks: foundation, frontiers and applications. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4840–4841
Shi C, Hu B, Zhao WX, Philip SY (2018) Heterogeneous information network embedding for recommendation. IEEE Trans Knowl Data Eng 31(2):357–370
Tang J, Qu M, Mei Q (2015) Pte: Predictive text embedding through largescale heterogeneous text networks. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1165–1174
Xiao J, Xu H, Gao H, Bian M, Li Y (2021) A weakly supervised semantic segmentation network by aggregating seed cues: the multi-object proposal generation perspective. ACM Trans Multimidia Comput Commun Appl 17(1s):1–19
Xu L, Wei X, Cao J, Yu PS (2017) Embedding of embedding (eoe) joint embedding for coupled heterogeneous networks. In: Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, pp. 741–749
Cai H, Zheng VW, Chang KC-C (2018) A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE Trans Knowl Data Eng 30(9):1616–1637
Dong Y, Chawla NV, Swami A (2017) metapath2vec: Scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 135–144
Fu T-Y, Lee W-C, Lei Z (2017) Hin2vec: Explore meta-paths in heterogeneous information networks for representation learning. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 1797–1806
Chen Y, Wang C (2017) Hine: Heterogeneous information network embedding. In: International Conference on Database Systems for Advanced Applications, pp. 180–195. Springer
Zhang J, Xia C, Zhang C, Cui L, Fu Y, Philip SY (2017) Bl-mne: emerging heterogeneous social network embedding through broad learning with aligned autoencoder. In: 2017 IEEE International Conference on Data Mining (ICDM), pp. 605–614. IEEE
Wang H, Zhang F, Hou M, Xie X, Guo M, Liu Q (2018) Shine: Signed heterogeneous information network embedding for sentiment link prediction. In: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 592–600
Hu B, Fang Y, Shi C (2019) Adversarial learning on heterogeneous information networks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 120–129
Gao H, Dai B, Miao H, Yang X, Barroso RJD, Walayat H (2022) A novel gapg approach to automatic property generation for formal verification: The gan perspective. ACM Trans Multi Comput Commun Appl (TOMM)
Zhao K, Bai T, Wu, B, Wang B, Zhang Y, Yang Y, Nie J-Y (20202) Deep adversarial completion for sparse heterogeneous information network embedding. In: Proceedings of The Web Conference 2020, pp. 508–518
Zhang C, Song D, Huang C, Swami A, Chawla NV (2019) Heterogeneous graph neural network. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 793–803
Chen J, Ying H, Liu X, Gu J, Feng R, Chen T, Gao H, Wu J (2020) A transfer learning based super-resolution microscopy for biopsy slice images: the joint methods perspective. IEEE/ACM Trans Computat Biol Bioinform 18(1):103–113
Gao H, Xu K, Cao M, Xiao J, Xu Q, Yin Y (2021) The deep features and attention mechanism-based method to dish healthcare under social iot systems: An empirical study with a hand-deep local-global net. IEEE Trans Computat Soc Syst 9(1):336–347
Gao H, Xiao J, Yin Y, Liu T, Shi J (2022) A mutually supervised graph attention network for few-shot segmentation: The perspective of fully utilizing limited samples. IEEE Trans Neural Netw Learn Syst
Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: European Semantic Web Conference, pp. 593–607. Springer
Yun S, Jeong M, Kim R, Kang J, Kim HJ (2019) Graph transformer networks. Advances in Neural Information Process Syst 32:11983–11993
Zhu S, Zhou C, Pan S, Zhu X, Wang B (2019) Relation structureaware heterogeneous graph neural network. In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 1534–1539. IEEE
Ma S, Liu J-W, Zuo X, Li W-M (2021) Heterogeneous graph gated attention network. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–6. IEEE
Tao Y, Li Y, Wu Z (2021) Revisiting graph neural networks for node classification in heterogeneous graphs. In: 2021 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6. IEEE
Acknowledgements
We would like to thank Professor Xin Wang and Zhiyong Feng from the College of Intelligence and Computing of Tianjin University for their valuable revising of the manuscript
Funding
This research was partially funded by the National Natural Science Foundation of China (NSFC), No. 61832014 and 61373165
Author information
Authors and Affiliations
Contributions
Conceptualization: Guozheng Rao, Ke Feng, Qing Cong, Li Zhang; Methodology: Guozheng Rao, Qing Cong, Ke Feng; Formal analysis and investigation: Qing Cong, Ke Feng; Writing - original draft preparation: Ke Feng, Guozheng Rao, Qing Cong, Li Zhang; Writing - review and editing: Li Zhang; Funding acquisition: Guozheng Rao; Resources: Qing Cong; Supervision: Guozheng Rao, Li Zhang
Corresponding authors
Ethics declarations
Conflicts of interest
The authors declare no conflicts of interest
Ethics approval
Not applicable
Consent to participate
Not applicable
Consent for publication
Not applicable
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Guozheng Rao, Li Zhang and Qing Cong these authors contributed equally to this work.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Feng, K., Rao, G., Zhang, L. et al. An interlayer feature fusion-based heterogeneous graph neural network. Appl Intell 53, 25626–25639 (2023). https://doi.org/10.1007/s10489-023-04840-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04840-w