Movatterモバイル変換

[0]ホーム
URL:

Skip to main content

Advertisement

Springer Nature Link
Log in

Multi-graph Fusion and Virtual Node Enhanced Graph Neural Networks

  • Conference paper
  • First Online:

Part of the book series:Lecture Notes in Computer Science ((LNCS,volume 15020))

Included in the following conference series:

  • 717Accesses

Abstract

Graph Neural Networks (GNNs) have emerged as a dominant tool for effectively learning from graph data, leveraging their remarkable learning capabilities. However, many GNN-based techniques assume complete and accurate graph relations. Unfortunately, this assumption often diverges from reality, as real-world scenarios frequently exhibit missing and erroneous edges within graphs. Consequently, GNNs that rely solely on the original graph structure inevitably lead to suboptimal results. To address this challenge, we propose a novel approach known asMulti-graph fusion andVirtual node enhancedGraphNeuralNetworks (MVGNN). Initially, we introduce an adaptive graph that complements the original and feature graphs. This adaptive graph serves to bridge gaps in the original and feature graphs, capturing missing edges and refining the graph’s structure. Subsequently, we merge the original, feature, and adaptive graphs by applying attention mechanisms. In addition, MVGNN strategically designs virtual nodes, which act as auxiliary elements, changing the propagation mode between low-weighted edges and further enhancing the robustness of the model. The proposed MVGNN is evaluated on six benchmark datasets, demonstrating its superiority over existing state-of-the-art classification methodologies.

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

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 8465
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 10581
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

References

  1. Fan, W., et al.: Graph neural networks for social recommendation. In: WWW (2019)

    Google Scholar 

  2. Wang, Z., Chen, J., Chen, H.: EGAT: edge-featured graph attention network. In: ICANN, (2021)

    Google Scholar 

  3. Zhu, Z., Xu, W., Cheng, X., Song, T., Zou, Y.: A dynamic graph interactive framework with label-semantic injection for spoken language understanding. In: ICASSP (2023)

    Google Scholar 

  4. Jin, W., Ma, Y., Liu, X., Tang, X., Wang, S., Tang, J.: Graph structure learning for robust graph neural networks. In: KDD (2020)

    Google Scholar 

  5. Wang, R., et al.: Graph structure estimation neural networks. In: WWW (2021)

    Google Scholar 

  6. Wang, X., Zhu, M., Bo, D., Cui, P., Shi, C., Pei, J.: AM-GCN: adaptive multi-channel graph convolutional networks. In: KDD (2020)

    Google Scholar 

  7. Liu, C., Wen, L., Kang, Z., Luo, G., Tian, L.: Self-supervised consensus representation learning for attributed graph. In: ACM MM (2021)

    Google Scholar 

  8. Zhu, M., Wang, X., Shi, C., Li, Y., Du, J.: Towards adaptive information fusion in graph convolutional networks. In: TKDE (2023)

    Google Scholar 

  9. Peng, X., Cheng, J., Tang, X., Liu, J., Wu, J.: Dual contrastive learning network for graph clustering. In: TNNLS (2023)

    Google Scholar 

  10. Rong, Y., Huang, W., Xu, T., Huang, J.: DropEdge: towards deep graph convolutional networks on node classification. In: ICLR (2020)

    Google Scholar 

  11. Feng, W., et al.: Graph random neural networks for semi-supervised learning on graphs. In: NIPS (2020)

    Google Scholar 

  12. Niu, S., Zhu, P., Hu, Q., Shi, H.: Adaptive graph fusion for unsupervised feature selection. In: ICANN (2019)

    Google Scholar 

  13. Fatemi, B., El Asri, L., Kazemi, S.M.: SLAPS: self-supervision improves structure learning for graph neural networks. In: NIPS (2021)

    Google Scholar 

  14. Zhu, Y., Xu, Y., Yu, F., Liu, Q., Wu, S., Wang, L.: Graph contrastive learning with adaptive augmentation. In: WWW (2021)

    Google Scholar 

  15. Zhang, Y., et al.: Adaptive graph attention network with temporal fusion for micro-expressions recognition. In: ICME (2023)

    Google Scholar 

  16. Qiu, J., et al: GCC: graph contrastive coding for graph neural network pre-training. In: KDD (2020)

    Google Scholar 

  17. Dehak, N., et al.: Cosine similarity scoring without score normalization techniques. Odyssey (2010)

    Google Scholar 

  18. Peterson, L.E.: K-nearest neighbor. Scholarpedia (2009)

    Google Scholar 

  19. Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)

    Google Scholar 

  20. Bojchevski, A., Günnemann, S.: Deep gaussian embedding of graphs: unsupervised inductive learning via ranking. In: ICLR (2018)

    Google Scholar 

  21. Meng, Z., Liang, S., Bao, H., Zhang, X.: Co-embedding attributed networks. WSDM (2019)

    Google Scholar 

  22. Wang, W., Liu, X., Jiao, P., Chen, X., Jin, D.: Pacific-asia conference on knowledge discovery and data mining. In: KDD (2018)

    Google Scholar 

  23. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: ICML (2018)

    Google Scholar 

  24. Abu-El-Haija, S, et al.: MixHop: higher-order graph convolutional architectures via sparsified neighborhood mixing. In: ICML (2019)

    Google Scholar 

  25. Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR (2008)

    Google Scholar 

Download references

Acknowledgement

This research was supported by National Natural Science Foundation of China under Grant 62172023, U19B2039, U1811463, 61806014; in part by Beijing Natural Science Foundation under Grant 4244085; in part by the Postdoctoral Fellowship Program of CPSF under Grant GZC20230203; in part by the China Postdoctoral Science Foundation under Grant 2023M740201; in part by Fundamental Research Funds for the Central Universities under Grant ZY2414. The authors would like to thank the anonymous reviewers and editors for their constructive comments and suggestions.

Author information

Authors and Affiliations

  1. Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China

    Yachao Yang, Yanfeng Sun, Shaofan Wang & Baocai Yin

  2. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, 100029, China

    Jipeng Guo

Authors
  1. Yachao Yang

    You can also search for this author inPubMed Google Scholar

  2. Yanfeng Sun

    You can also search for this author inPubMed Google Scholar

  3. Jipeng Guo

    You can also search for this author inPubMed Google Scholar

  4. Shaofan Wang

    You can also search for this author inPubMed Google Scholar

  5. Baocai Yin

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence toYanfeng Sun.

Editor information

Editors and Affiliations

  1. IDSIA USI-SUPSI, Lugano, Switzerland

    Michael Wand

  2. Comenius University, Bratislava, Slovakia

    Kristína Malinovská

  3. KAUST Center of Generative AI, Thuwal, Saudi Arabia

    Jürgen Schmidhuber

  4. Helmholtz Zentrum München, Neuherberg, Germany

    Igor V. Tetko

Rights and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Yang, Y., Sun, Y., Guo, J., Wang, S., Yin, B. (2024). Multi-graph Fusion and Virtual Node Enhanced Graph Neural Networks. In: Wand, M., Malinovská, K., Schmidhuber, J., Tetko, I.V. (eds) Artificial Neural Networks and Machine Learning – ICANN 2024. ICANN 2024. Lecture Notes in Computer Science, vol 15020. Springer, Cham. https://doi.org/10.1007/978-3-031-72344-5_13

Download citation

Publish with us

Access this chapter

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 8465
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 10581
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide -see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

[8]ページ先頭
©2009-2025 Movatter.jp