Abstract
Heterogeneous Graph (HG) is a data structure composed of various types of nodes and rich relational information, which can accurately show complex application scenarios in the real world. Although heterogeneous graph neural networks (HGNNs) have been widely applied to model HGs, there are still some issues that need to be addressed. On the one hand, most of HGNNs ignore the fine-grained information when modeling HGs, such as attribute and topology overcoupling due to the accumulation of multi-source heterogeneous information in message passing. On the other hand, HGNNs are designed from a single view (based on metapath or relation awareness), which undoubtedly leads to information loss and makes it difficult to fully extract potential interactions in HGs. To tackle the aforementioned limitations, a Multi-view fusion based Heterogeneous Graph Neural Network (MHGNN) is proposed, which is modeled from node view, network schema view, and semantics view to mine the information from different granularity in HGs. MHGNN extracts the fine-gained information of nodes, heterogeneous interaction of neighboring nodes, and mutual influence between different semantics from three views respectively. Then, the model integrates these information as the final node representation. To prove the effectiveness of this work, extensive experiments are conducted on four real-world datasets, and comparisons are made with seven competitive baselines. The results demonstrate that the proposed MHGNN significantly outperforms state-of-the-art methods. Source codes are available at https://github.com/ZZY-GraphMiningLab/MHGNN.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Figg_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10489-024-05567-y/MediaObjects/10489_2024_5567_Fig8_HTML.png)
Similar content being viewed by others
Availability of supporting data
The datasets used in the experiments are publicly available in the online repository.
References
Sun Y, Han J (2013) Mining heterogeneous information networks. ACM SIGKDD Explor Newsletter 14(2):20–28. https://doi.org/10.1145/2481244.2481248
Wang X, Bo D, Shi C, Fan S, Ye Y, Philip SY (2022) A survey on heterogeneous graph embedding: methods, techniques, applications and sources. IEEE Trans Big Data 9(2):415–436. https://doi.org/10.1109/TBDATA.2022.3177455
Li C, Liu X, Yan Y, Zhao Z, Zeng Q (2023) Hetgnn-sf: Self-supervised learning on heterogeneous graph neural network via semantic strength and feature similarity. Appl Intell, 1–18. https://doi.org/10.1007/s10489-023-04612-6
Li C, Fu J, Yan Y, Zhao Z, Zeng Q (2024) Higher order heterogeneous graph neural network based on node attribute enhancement. Expert Syst Appl 238:122404. https://doi.org/10.1016/j.eswa.2023.122404
Gao C, Zheng Y, Li N, Li Y, Qin Y, Piao J, Quan Y, Chang J, ** D, He X et al (2023) A survey of graph neural networks for recommender systems: challenges, methods, and directions. ACM Trans Recommender Syst 1(1):1–51. https://doi.org/10.1145/3568022
Wang H, Zhou K, Zhao X, Wang J, Wen J-R (2023) Curriculum pre-training heterogeneous subgraph transformer for top-n recommendation. ACM Trans Inf Syst 41(1):1–28. https://doi.org/10.1145/3528667
Yang T, Hu L, Shi C, Ji H, Li X, Nie L (2021) Hgat: Heterogeneous graph attention networks for semi-supervised short text classification. ACM Trans Inf Syst 39(3):1–29. https://doi.org/10.18653/v1/D19-1488
Gao D, Li K, Wang R, Shan S, Chen X (2020) Multi-modal graph neural network for joint reasoning on vision and scene text. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12746–12756. https://doi.org/10.1109/cvpr42600.2020.01276
Malekzadeh M, Hajibabaee P, Heidari M, Zad S, Uzuner O, Jones JH (2021) Review of graph neural network in text classification. In: 2021 IEEE 12th Annual ubiquitous computing, electronics & mobile communication conference (UEMCON), pp 0084–0091. IEEE. https://doi.org/10.1109/UEMCON53757.2021.9666633
Hu L, Xu S, Li C, Yang C, Shi C, Duan N, **e X, Zhou M (2020) Graph neural news recommendation with unsupervised preference disentanglement. In: Proceedings of the 58th annual meeting of the association for computational linguistics, pp 4255–4264. https://doi.org/10.18653/v1/2020.acl-main.392
Hou S, Ye Y, Song Y, Abdulhayoglu M (2017) Hindroid: An intelligent android malware detection system based on structured heterogeneous information network. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1507–1515. https://doi.org/10.1145/3097983.3098026
Louis A, Van Dijck G, Spanakis G (2023) Finding the law: Enhancing statutory article retrieval via graph neural networks. In: Proceedings of the 17th conference of the european chapter of the association for computational linguistics, pp 2753–2768. https://doi.org/10.48550/ar**v.2301.12847
Li C, Peng H, Li J, Sun L, Lyu L, Wang L, Philip SY, He L (2021) Joint stance and rumor detection in hierarchical heterogeneous graph. IEEE Trans Neural Netw Learn Syst 33(6):2530–2542. https://doi.org/10.1109/TNNLS.2021.3114027
Qian L, Wang J, Lin H, Xu B, Yang L (2022) Heterogeneous information network embedding based on multiperspective metapath for question routing. Knowl-Based Syst 240:107842. https://doi.org/10.1016/j.knosys.2021.107842
Yang Y, Guan Z, Li J, Zhao W, Cui J, Wang Q (2023) Interpretable and efficient heterogeneous graph convolutional network. IEEE Trans Knowl Data Eng 35(02):1637–1650. https://doi.org/10.1109/TKDE.2021.3101356
Fu X, Zhang J, Meng Z, King I (2020) Magnn: Metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of The Web Conference 2020, pp 2331–2341. https://doi.org/10.1145/3366423.3380297
Wang X, Liu N, Han H, Shi C (2021) Self-supervised heterogeneous graph neural network with co-contrastive learning. In: Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, pp 1726–1736. https://doi.org/10.1145/3447548.3467415
Yan Y, Li C, Yu Y, Li X, Zhao Z (2023) Osgnn: Original graph and subgraph aggregated graph neural network. Expert Syst Appl 225:120115. https://doi.org/10.1016/j.eswa.2023.120115
Li J, Peng H, Cao Y, Dou Y, Zhang H, Philip SY, He L (2021) Higher-order attribute-enhancing heterogeneous graph neural networks. IEEE Trans Knowl Data Eng 35(1):560–574. https://doi.org/10.1109/TKDE.2021.3074654
Hosseini SA, Abbaszadeh Shahri A, Asheghi R (2022) Prediction of bedload transport rate using a block combined network structure. Hydrol Sci J 67(1):117–128. https://doi.org/10.1080/02626667.2021.2003367
Cui P, Wang X, Pei J, Zhu W (2018) A survey on network embedding. IEEE Trans Knowl Data Eng 31(5):833–852. https://doi.org/10.1109/TKDE.2018.2849727
Lei R, Zhen W, Li Y, Ding B, Wei Z (2022) Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks. In: Advances in neural information processing systems. https://doi.org/10.48550/ar**v.2205.13892
Bruna J, Zaremba W, Szlam A, Lecun Y (2014) Spectral networks and locally connected networks on graphs. In: International conference on learning representations (ICLR2014), CBLS, April 2014, p. https://doi.org/10.48550/ar**v.1312.6203
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. In: International conference on learning representations. https://doi.org/10.48550/ar**v.1609.02907
Wang X, Zhang M (2022) How powerful are spectral graph neural networks. In: International conference on machine learning, pp 23341–23362. PMLR. https://doi.org/10.48550/ar**v.2205.11172
Yang L, Chen C, Li W, Niu B, Gu J, Wang C, He D, Guo Y, Cao X (2022) Self-supervised graph neural networks via diverse and interactive message passing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp 4327–4336. https://doi.org/10.1609/aaai.v36i4.20353
Mo Y, Peng L, Xu J, Shi X, Zhu X (2022) Simple unsupervised graph representation learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 7797–7805. https://doi.org/10.1609/aaai.v36i7.20748
Hamilton WL, Ying R, Leskovec J (2017) Inductive representation learning on large graphs. In: Proceedings of the 31st International conference on neural information processing systems, pp 1025–1035. CorpusID: 4755450
Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018) Graph attention networks. In: International conference on learning representations. https://doi.org/10.48550/ar**v.1710.10903
Chen D, O’Bray L, Borgwardt K (2022) Structure-aware transformer for graph representation learning. In: International conference on machine learning, pp 3469–3489. PMLR. CorpusID: 246634635
Asheghi R, Hosseini SA, Saneie M, Shahri AA (2020) Updating the neural network sediment load models using different sensitivity analysis methods: a regional application. J Hydroinformatics 22(3):562–577. https://doi.org/10.2166/hydro.2020.098
Guha S, Kodipalli A (2023) Sensitivity analysis of physical and mental health factors affecting polycystic ovary syndrome in women. Expert Syst 13413. https://doi.org/10.1111/exsy.13413
Firouzi B, Abbasi A, Sendur P, Zamanian M, Chen H (2023) Enhancing the performance of piezoelectric energy harvester under electrostatic actuation using a robust metaheuristic algorithm. Eng Appl Artif Intell 118:105619. https://doi.org/10.1016/j.engappai.2022.105619
Abbaszadeh Shahri A, Shan C, Larsson S (2022) A novel approach to uncertainty quantification in groundwater table modeling by automated predictive deep learning. Nat Resour Res 31(3):1351–1373. https://doi.org/10.1007/s11053-022-10051-w
Yun S, Jeong M, Kim R, Kang J, Kim HJ (2019) Graph transformer networks. Adv Neural Inf Process Syst32. CorpusID: 202763464
Zhao J, Wang X, Shi C, Hu B, Song G, Ye Y (2021) Heterogeneous graph structure learning for graph neural networks. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 4697–4705. https://doi.org/10.1609/aaai.v35i5.16600
Wang Z, Yu D, Li Q, Shen S, Yao S (2023) Sr-hgn: Semantic-and relation-aware heterogeneous graph neural network. Expert Syst Appl 224:119982. https://doi.org/10.1016/j.eswa.2023.119982
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. https://doi.org/10.1145/3308558.3313562
Fu X, King I (2024) Mecch: metapath context convolution-based heterogeneous graph neural networks. Neural Netw 170:266–275. https://doi.org/10.1145/3366423.3380297
Zhang M, Wang X, Zhu M, Shi C, Zhang Z, Zhou J (2022) Robust heterogeneous graph neural networks against adversarial attacks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 36, pp 4363–4370. https://doi.org/10.1609/aaai.v36i4.20357
Ji H, Wang X, Shi C, Wang B, Philip SY (2023) Heterogeneous graph propagation network. IEEE Trans Knowl Data Eng 35(01):521–532. https://doi.org/10.1109/TKDE.2021.3079239
Gasteiger J, Bojchevski A, Günnemann S (2018) Predict then propagate: graph neural networks meet personalized pagerank. In: International conference on learning representations. https://doi.org/10.48550/ar**v.1810.05997
Acknowledgements
This work is supported by National Key R &D Program of China(Grant No.2022ZD0119501); the National Natural Science Foundation of China (Grant No. 62072288, 52374221, 62302277), the Natural Science Foundation of Shandong Province (Grant No. ZR2022MF268, ZR2022QF136, ZR2021QG038), the Taishan Scholar Program of Shandong Province(Grant No.tsqn202211154, ts20190936), the Natural Science Foundation of Shandong Province (Youth Program, Grant No.ZR2022QF136).
Author information
Authors and Affiliations
Contributions
Chao Li, **angkai Zhu, Yeyu Yan, Zhongying Zhao, Lingtao Su, Qingtian Zeng wrote the main manuscript text; **angkai Zhu and Yeyu Yan prepared the result of our experiments; All authors reviewed the manuscript.
Corresponding authors
Ethics declarations
Ethical Approval
Not applicable.
Consent to participate
There is the consent of all authors.
Human and Animal Ethics
Not applicable.
Consent for publication
There is the consent of all authors.
Competing interests
The authors declare that there is no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Li, C., Zhu, X., Yan, Y. et al. MHGNN: Multi-view fusion based Heterogeneous Graph Neural Network. Appl Intell (2024). https://doi.org/10.1007/s10489-024-05567-y
Accepted:
Published:
DOI: https://doi.org/10.1007/s10489-024-05567-y