Skip to main content
SpringerLink
Log in

Heterogeneous graph neural network with graph-data augmentation and adaptive denoising

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Heterogeneous graphs are especially important in our daily life, which describe objects and their connections through nodes and edges. For this complex network structure, many heterogeneous graph neural networks have been designed, but the traditional heterogeneous graph neural network has several obvious shortcomings: (1) Models using meta-paths require selection of meta-paths, failing to learn all meta-paths in the dataset, and cannot capture structural information beyond meta-paths. (2) Models that do not apply meta-paths will be limited by the relationships of the original graph. Due to the absence or omission of some very important but costly relationships in the dataset, the ability of the model to learn node features is limited. (3) The existence of noise will affect the optimization of the parameters of the heterogeneous graph neural network models. In response to these problems, we propose our model: Heterogeneous Graph Neural Network with Graph-data Augmentation and Adaptive Denoising (GAAD). We hope that our model is not affected by differences in graph structure and noise nodes in the graph structure. In summary, we hope that our model can adapt to most graph structures. So we propose a method based on graph neural network to mine the hidden relationship between heterogeneous nodes, calculate the possibility of the existence of edges between heterogeneous nodes, strengthen the graph structure by adding highly possible edges, enrich the information transmission between nodes. Then we apply an adaptive noise reduction algorithm to prevent the possible noise diffusion caused by data enhancement in the graph structure. Extensive experiments on three real-world network datasets demonstrate the superiority of GAAD over the state-of-the-art methods. The code is available on https://github.com/xiaojunlou0831/GAAD.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Berton L, Valverde-Rebaza J, de Andrade Lopes A (2015) Link prediction in graph construction for supervised and semi-supervised learning. In: 2015 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE

  2. Bhagat S, Cormode G, Muthukrishnan S (2011) Node classification in social networks. In: Social network data analytics, pages 115–148. Springer,

  3. Bo D, Hu BB, Wang X, Zhang Z, Shi C, Zhou J (2022) Regularizing graph neural networks via consistency-diversity graph augmentations. Proceedings of the AAAI Conference on Artificial Intelligence 36:3913–3921

    Article  Google Scholar 

  4. Chang Y, Chen C, Hu W, Zheng Z, Zhou X, Chen S (2022) Megnn: meta-path extracted graph neural network for heterogeneous graph representation learning. Knowledge-Based Systems 235:107611

    Article  Google Scholar 

  5. Chen M, Huang C, Xia L, Wei W, Xu Y, Luo R (2023) Heterogeneous graph contrastive learning for recommendation. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, pages 544–552

  6. Dawid AP, Skene AM (1979) Maximum likelihood estimation of observer error-rates using the em algorithm. Journal of the Royal Statistical Society: Series C (Applied Statistics) 28(1):20–28

    Google Scholar 

  7. DeVries T, Taylor GW (2017) Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552

  8. Dong X, Zhang Y, Pang K, Chen F, Lu M (2022) Heterogeneous graph neural networks with denoising for graph embeddings. Knowledge-Based Systems 238:107899

    Article  Google Scholar 

  9. 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, pages 135–144

  10. 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

    Google Scholar 

  11. Gong C, Wang D, Li M, Chandra V, Liu Q (2021) Keepaugment: a simple information-preserving data augmentation approach. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1055–1064

  12. Goyal P, Ferrara E (2018) Graph embedding techniques, applications, and performance: a survey. Knowledge-Based Systems 151:78–94

    Article  Google Scholar 

  13. Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Advances in Neural Information Processing Systems 30

  14. Hamilton WL, Ying R, Leskovec J (2017) Representation learning on graphs: Methods and applications. arXiv:1709.05584

  15. Hickey RJ (1996) Noise modelling and evaluating learning from examples. Artif Intell 82(1–2):157–179

    Article  MathSciNet  Google Scholar 

  16. Hong H, Guo H, Lin Y, Yang X, Li Z, Ye J (2020) An attention-based graph neural network for heterogeneous structural learning. Proceedings of the AAAI Conference on Artificial Intelligence 34:4132–4139

    Article  Google Scholar 

  17. Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907

  18. Kipf TN, Welling M (2016) Variational graph auto-encoders. arXiv:1611.07308

  19. Kunegis J, Lommatzsch A (2009) Learning spectral graph transformations for link prediction. In: Proceedings of the 26th Annual International Conference on Machine Learning, pages 561–568

  20. Kuo C-W, Ma C-Y, Huang J-B, Kira Z (2020) Featmatch: feature-based augmentation for semi-supervised learning. In: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XVIII 16, pages 479–495. Springer

  21. Li J, Peng H, Cao Y, Dou Y, Zhang H, Yu P, He L (2021) Higher-order attribute-enhancing heterogeneous graph neural networks. IEEE Transactions on Knowledge and Data Engineering

  22. Lim S, Kim I, Kim T, Kim C, Kim S (2019) Fast autoaugment. Advances in Neural Information Processing Systems 32

  23. 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, pages 1150–1160

  24. Ou M, Cui P, Pei J, Zhang Z, Zhu W (2016) Asymmetric transitivity preserving graph embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1105–1114

  25. Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 701–710

  26. 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, pages 593–607. Springer, 2018

  27. Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):1–48

    Article  Google Scholar 

  28. Shorten C, Khoshgoftaar TM, Furht B (2021) Text data augmentation for deep learning. J Big Data 8:1–34

    Article  Google Scholar 

  29. Velickovic P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. Stat 1050:20

    Google Scholar 

  30. Verma V, Lamb A, Beckham C, Najafi A, Mitliagkas I, Lopez-Paz D, Bengio Y (2019) Manifold mixup: better representations by interpolating hidden states. In: International conference on machine learning, pages 6438–6447. PMLR

  31. Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1225–1234

  32. Wang W, Feng F, He X, Nie L, Chua T-S (2021) Denoising implicit feedback for recommendation. In: Proceedings of the 14th ACM international conference on web search and data mining, pages 373–381

  33. 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, pages 2022–2032

  34. Xiang R, Chersoni E, Lu Q, Huang C-R, Li W, Long Y (2021) Lexical data augmentation for sentiment analysis. J Assoc Inf Sci Technolo 72(11):1432–1447

    Article  Google Scholar 

  35. Xu M (2021) Understanding graph embedding methods and their applications. SIAM Rev 63(4):825–853

    Article  MathSciNet  Google Scholar 

  36. Yang Y, Guan Z, Li J, Zhao W, Cui J, Wang Q (2021) Interpretable and efficient heterogeneous graph convolutional network. IEEE Transactions on Knowledge and Data Engineering

  37. Ying Z, You J, Morris C, Ren X, Hamilton W, Leskovec J (2018) Hierarchical graph representation learning with differentiable pooling. Advances in Neural Information Processing Systems 31

  38. You Y, Chen T, Sui Y, Chen T, Wang Z, Shen Y (2020) Graph contrastive learning with augmentations. Adv Neural Inf Process Syst 33:5812–5823

    Google Scholar 

  39. Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) Cutmix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE/CVF international conference on computer vision, pages 6023–6032

  40. Yun S, Jeong M, Kim R, Kang J, Kim HJ (2019) Graph transformer networks. Advances in Neural Information Processing Systems, 32

  41. 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, pages 793–803

  42. Zhang M, Chen Y (2018) Link prediction based on graph neural networks. Advances in Neural Information Processing Systems, 31

  43. Zhao T, Liu Y, Neves L, Woodford O, Jiang M, Shah N (2021) Data augmentation for graph neural networks. Proceedings of the aaai conference on artificial intelligence 35:11015–11023

  44. Zhong Z, Zheng L, Kang G, Li S, Yang Y (2020) Random erasing data augmentation. Proceedings of the AAAI conference on artificial intelligence 34:13001–13008

    Article  Google Scholar 

  45. Zhu P, Yao X, Wang Y, Cao M, Hui B, Zhao S, Hu Q (2022) Latent heterogeneous graph network for incomplete multi-view learning. IEEE Transactions on Multimedia

Download references

Acknowledgements

The paper is supported by the Key R &D Projects in Zhejiang Province (2022C02009).

Author information

Authors and Affiliations

  1. School of Mathematics and Computer Science, Zhejiang A & F University, Hangzhou, 311300, China

    Xiaojun Lou & Jian Li

  2. The Key Laboratory of Embedded System and Service Computing of Ministry of Education, Tongji University, Shanghai, 201804, China

    Guanjun Liu

Authors
  1. Xiaojun Lou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guanjun Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jian Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jian Li.

Ethics declarations

Conflict of Interests

The authors declare no conflict of interest.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lou, X., Liu, G. & Li, J. Heterogeneous graph neural network with graph-data augmentation and adaptive denoising. Appl Intell 54, 4411–4424 (2024). https://doi.org/10.1007/s10489-024-05363-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-024-05363-8

Keywords

Search

Navigation