Skip to main content

Advertisement

Springer Nature Link
Log in

Learning from shortcut: a shortcut-guided approach for explainable graph learning

  • Research Article
  • Published:
Frontiers of Computer Science Aims and scope Submit manuscript

Abstract

The remarkable success in graph neural networks (GNNs) promotes the explainable graph learning methods. Among them, the graph rationalization methods draw significant attentions, which aim to provide explanations to support the prediction results by identifying a small subset of the original graph (i.e., rationale). Although existing methods have achieved promising results, recent studies have proved that these methods still suffer from exploiting shortcuts in the data to yield task results and compose rationales. Different from previous methods plagued by shortcuts, in this paper, we propose a Shortcut-guided Graph Rationalization (SGR) method, which identifies rationales by learning from shortcuts. Specifically, SGR consists of two training stages. In the first stage, we train a shortcut guider with an early stop strategy to obtain shortcut information. During the second stage, SGR separates the graph into the rationale and non-rationale subgraphs. Then SGR lets them learn from the shortcut information generated by the frozen shortcut guider to identify which information belongs to shortcuts and which does not. Finally, we employ the non-rationale subgraphs as environments and identify the invariant rationales which filter out the shortcuts under environment shifts. Extensive experiments conducted on synthetic and real-world datasets provide clear validation of the effectiveness of the proposed SGR method, underscoring its ability to provide faithful explanations.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. 2017

    MATH  Google Scholar 

  2. Wu Z, Gan Y, Xu T, Wang F. Graph-segmenter: graph transformer with boundary-aware attention for semantic segmentation. Frontiers of Computer Science, 2024, 18(5): 185327.

    Article  Google Scholar 

  3. Liang Y, Song Q, Zhao Z, Zhou H, Gong M. BA-GNN: behavior-aware graph neural network for session-based recommendation. Frontiers of Computer Science, 2023, 17(6): 176613.

    Article  Google Scholar 

  4. Wu Y, Huang H, Song Y, Jin H. Soft-GNN: towards robust graph neural networks via self-adaptive data utilization. Frontiers of Computer Science, 2025, 19(4): 194311.

    Article  Google Scholar 

  5. Hu W, Fey M, Zitnik M, Dong Y, Ren H, Liu B, Catasta M, Leskovec J. Open graph benchmark: datasets for machine learning on graphs. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1855

    Google Scholar 

  6. Guo Z, Zhang C, Yu W, Herr J, Wiest O, Jiang M, Chawla N V. Few-shot graph learning for molecular property prediction. In: Proceedings of the Web Conference 2021. 2021, 2559–2567

    Chapter  MATH  Google Scholar 

  7. Yehudai G, Fetaya E, Meirom E A, Chechik G, Maron H. From local structures to size generalization in graph neural networks. In: Proceedings of the 38th International Conference on Machine Learning. 2021, 11975–11986

    MATH  Google Scholar 

  8. Ying R, Bourgeois D, You J, Zitnik M, Leskovec J. GNNExplainer: generating explanations for graph neural networks. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 829

    Google Scholar 

  9. Luo D, Cheng W, Xu D, Yu W, Zong B, Chen H, Zhang X. Parameterized explainer for graph neural network. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1646

    MATH  Google Scholar 

  10. Lei T, Barzilay R, Jaakkola T. Rationalizing neural predictions. In: Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing. 2016, 107–117

    Chapter  MATH  Google Scholar 

  11. Wang X, Wu Y X, Zhang A, He X, Chua T S. Towards multi-grained explainability for graph neural networks. In: Proceedings of the 35th International Conference on Neural Information Processing Systems. 2024, 1410

    MATH  Google Scholar 

  12. Chang S, Zhang Y, Yu M, Jaakkola T S. Invariant rationalization. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 1448–1458

    MATH  Google Scholar 

  13. Wu Y, Wang X, Zhang A, He X, Chua T S. Discovering invariant rationales for graph neural networks. In: Proceedings of the 10th International Conference on Learning Representations. 2022

    MATH  Google Scholar 

  14. Fan S, Wang X, Mo Y, Shi C, Tang J. Debiasing graph neural networks via learning disentangled causal substructure. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1808

    MATH  Google Scholar 

  15. Sui Y, Wang X, Wu J, Lin M, He X, Chua T S. Causal attention for interpretable and generalizable graph classification. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022, 1696–1705

    Chapter  MATH  Google Scholar 

  16. Li H, Zhang Z, Wang X, Zhu W. Learning invariant graph representations for out-of-distribution generalization. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 859

    MATH  Google Scholar 

  17. Clark C, Yatskar M, Zettlemoyer L. Don’t take the easy way out: ensemble based methods for avoiding known dataset biases. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019, 4067–4080

    MATH  Google Scholar 

  18. Nam J, Cha H, Ahn S, Lee J, Shin J. Learning from failure: training debiased classifier from biased classifier. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. 2020, 1736

    MATH  Google Scholar 

  19. Li Y, Lyu X, Koren N, Lyu L, Li B, Ma X. Anti-backdoor learning: training clean models on poisoned data. In: Proceedings of the 34th Advances in Neural Information Processing Systems. 2021, 14900–14912

    MATH  Google Scholar 

  20. Arpit D, Jastrzębski S, Ballas N, Krueger D, Bengio E, Kanwal M S, Maharaj T, Fischer A, Courville A, Bengio Y, Lacoste-Julien S. A closer look at memorization in deep networks. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 233–242

    MATH  Google Scholar 

  21. Poole B, Ozair S, Van Den Oord A, Alemi A A, Tucker G. On variational bounds of mutual information. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 5171–5180

    Google Scholar 

  22. Cheng P, Hao W, Dai S, Liu J, Gan Z, Carin L. CLUB: a contrastive log-ratio upper bound of mutual information. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 166

    Google Scholar 

  23. Yue L, Liu Q, Du Y, An Y, Wang L, Chen E. DARE: disentanglement-augmented rationale extraction. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1929

    MATH  Google Scholar 

  24. van den Oord A, Li Y, Vinyals O. Representation learning with contrastive predictive coding. 2018, arXiv preprint arXiv: 1807.03748

    MATH  Google Scholar 

  25. Luo J, He M, Pan W, Ming Z. BGNN: behavior-aware graph neural network for heterogeneous session-based recommendation. Frontiers of Computer Science, 2023, 17(5): 175336.

    Article  Google Scholar 

  26. Xiao S, Bai T, Cui X, Wu B, Meng X, Wang B. A graph-based contrastive learning framework for medicare insurance fraud detection. Frontiers of Computer Science, 2023, 17(2): 172341.

    Article  MATH  Google Scholar 

  27. Schlichtkrull M S, De Cao N, Titov I. Interpreting graph neural networks for NLP with differentiable edge masking. In: Proceedings of the 9th International Conference on Learning Representations. 2021

    MATH  Google Scholar 

  28. Velickovic P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y. Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations. 2018

    MATH  Google Scholar 

  29. Chen Y, Zhang Y, Bian Y, Yang H, Ma K, Xie B, Liu T, Han B, Cheng J. Learning causally invariant representations for out-of-distribution generalization on graphs. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 1608

    MATH  Google Scholar 

  30. Li H, Wang X, Zhang Z, Zhu W. Out-of-distribution generalization on graphs: a survey. 2022, arXiv preprint arXiv: 2202.07987

    MATH  Google Scholar 

  31. Yang N, Zeng K, Wu Q, Jia X, Yan J. Learning substructure invariance for out-of-distribution molecular representations. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 942

    MATH  Google Scholar 

  32. Wang F, Liu Q, Chen E, Huang Z, Yin Y, Wang S, Su Y. NeuralCD: a general framework for cognitive diagnosis. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(8): 8312–8327.

    Article  MATH  Google Scholar 

  33. Liu G, Zhao T, Xu J, Luo T, Jiang M. Graph rationalization with environment-based augmentations. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2022, 1069–1078

    Chapter  MATH  Google Scholar 

  34. Tishby N, Pereira F C, Bialek W. The information bottleneck method. 2000, arXiv preprint arXiv: physics/0004057

    MATH  Google Scholar 

  35. Alemi A A, Fischer I, Dillon J V, Murphy K. Deep variational information bottleneck. In: Proceedings of the 5th International Conference on Learning Representations. 2017

    MATH  Google Scholar 

  36. Paranjape B, Joshi M, Thickstun J, Hajishirzi H, Zettlemoyer L. An information bottleneck approach for controlling conciseness in rationale extraction. In: Proceedings of 2020 Conference on Empirical Methods in Natural Language Processing. 2020, 1938–1952

    Google Scholar 

  37. Wu T, Ren H, Li P, Leskovec J. Graph information bottleneck. In: Proceedings of the 34th Advances in Neural Information Processing Systems. 2020, 20437–20448

    Google Scholar 

  38. Yu J, Xu T, Rong Y, Bian Y, Huang J, He R. Graph information bottleneck for subgraph recognition. In: Proceedings of the 9th International Conference on Learning Representations. 2021

    MATH  Google Scholar 

  39. Miao S, Liu M, Li P. Interpretable and generalizable graph learning via stochastic attention mechanism. In: Proceedings of the 39th International Conference on Machine Learning. 2022, 15524–15543

    MATH  Google Scholar 

  40. Geirhos R, Jacobsen J H, Michaelis C, Zemel R, Brendel W, Bethge M, Wichmann F A. Shortcut learning in deep neural networks. Nature Machine Intelligence, 2020, 2(11): 665–673.

    Article  Google Scholar 

  41. Du M, He F, Zou N, Tao D, Hu X. Shortcut learning of large language models in natural language understanding: a survey. 2022, arXiv preprint arXiv: 2208.11857

    MATH  Google Scholar 

  42. Yue L, Liu Q, Wang L, An Y, Du Y, Huang Z. Interventional rationalization. In: Proceedings of 2023 Conference on Empirical Methods in Natural Language Processing. 2023, 11404–11418

    Chapter  MATH  Google Scholar 

  43. Yue L, Liu Q, Du Y, Wang L, Gao W, An Y. Towards faithful explanations: Boosting rationalization with shortcuts discovery. In: Proceedings of the 12th International Conference on Learning Representations. 2024

    MATH  Google Scholar 

  44. Rashid A, Lioutas V, Rezagholizadeh M. MATE-KD: Masked adversarial TExt, a companion to knowledge distillation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021, 1062–1071

    Google Scholar 

  45. Stacey J, Minervini P, Dubossarsky H, Riedel S, Rocktäschel T. Avoiding the hypothesis-only bias in natural language inference via ensemble adversarial training. In: Proceedings of 2020 Conference on Empirical Methods in Natural Language Processing. 2020, 8281–8291

    Google Scholar 

  46. Arjovsky M, Bottou L, Gulrajani I, Lopez-Paz D. Invariant risk minimization. 2019, arXiv preprint arXiv: 1907.02893

    Google Scholar 

  47. Sanh V, Wolf T, Belinkov Y, Rush A M. Learning from others’ mistakes: Avoiding dataset biases without modeling them. In: Proceedings of the 9th International Conference on Learning Representations. 2021

    MATH  Google Scholar 

  48. Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks? In: Proceedings of the 7th International Conference on Learning Representations. 2019

    MATH  Google Scholar 

  49. Liu G, Inae E, Luo T, Jiang M. Rationalizing graph neural networks with data augmentation. ACM Transactions on Knowledge Discovery from Data, 2024, 18(4): 86.

    Article  Google Scholar 

  50. Socher R, Perelygin A, Wu J, Chuang J, Manning C D, Ng A, Potts C. Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of 2013 Conference on Empirical Methods in Natural Language Processing. 2013, 1631–1642

    Chapter  Google Scholar 

  51. Yu M, Chang S, Zhang Y, Jaakkola T. Rethinking cooperative rationalization: Introspective extraction and complement control. In: Proceedings of 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019, 4094–4103

    MATH  Google Scholar 

  52. Sun R, Tao H, Chen Y, Liu Q. HACAN: a hierarchical answer-aware and context-aware network for question generation. Frontiers of Computer Science, 2024, 18(5): 185321.

    Article  Google Scholar 

  53. Kingma D P, Ba J. Adam: a method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations. 2015

    MATH  Google Scholar 

Download references

Acknowledgements

This research was supported by grants from the Joint Research Project of the Science and Technology Innovation Community in Yangtze River Delta (No. 2023CSJZN0200), the National Natural Science Foundation of China (Grant No. 62337001) and the Fundamental Research Funds for the Central Universities.

Author information

Authors and Affiliations

  1. State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, 230026, China

    Linan Yue, Qi Liu, Ye Liu, Weibo Gao & Fangzhou Yao

  2. Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, 230026, China

    Qi Liu

Authors
  1. Linan Yue
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Qi Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Ye Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Weibo Gao
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Fangzhou Yao
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Qi Liu.

Ethics declarations

Competing interests The authors declare that they no competing interests or financial conflicts to disclose.

Additional information

Linan Yue received the BE degree in computer science from Hehai University, China in 2019. He is currently pursuing the PhD degree in data science with University of Science and Technology of China under the advisory of Prof. Qi Liu. He has published several papers in referred journals and conference proceedings, such as IEEE TKDE, NeurIPS, ICLR, SIGIR, SIGKDD, and WWW conference. His current research interests include graph data mining, and trustworthy AI.

Qi Liu received the PhD degree from the University of Science and Technology of China (USTC), China in 2013. He is currently a professor with State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China (USTC), China. His research interests include data mining, machine learning, and trustworthy AI. He has published prolifically in refereed journals and conference proceedings (e.g., TKDE, TOIS, KDD). He is an Associate Editor of IEEE TBD and Neurocomputing, and the Young Associate Editor of FCS. He was the recipient of KDD’ 18 Best Student Paper Award and ICDM’ 11 Best Research Paper Award. He was also the recipient of China Outstanding Youth Science Foundation, in 2019.

Ye Liu is currently pursuing his PhD in the School of Data Science at the University of Science and Technology of China, China under the advisory of Prof. E. Chen, and is a member of State Key Laboratory of Cognitive Intelligence. His current research interests encompass graph learning and trustworthy AI. He has published several papers in referred journals and conference proceedings, such as ACM TKDD, IJCAI, and ACL conference.

Weibo Gao received his BE degree from the School of Software at Hefei University of Technology, China in 2019. He is currently pursuing a PhD in the School of Computer Science and Technology at the University of Science and Technology of China, China under the guidance of Prof. Qi Liu. He has contributed to numerous publications in reputable conference proceedings, including SIGIR, AAAI, and NeurIPS conference. His current research interests encompass data mining and trustworthy AI.

Fangzhou Yao is currently pursuing her PhD in the School of Data Science at the University of Science and Technology of China, China under the advisory of Prof. Qi Liu, and is a member of State Key Laboratory of Cognitive Intelligence. Her current research interests encompass machine learning and trustworthy AI. She has published several papers in referred conference proceedings, such as IJCAI and WWW conference.

Electronic supplementary material

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yue, L., Liu, Q., Liu, Y. et al. Learning from shortcut: a shortcut-guided approach for explainable graph learning. Front. Comput. Sci. 19, 198338 (2025). https://doi.org/10.1007/s11704-024-40452-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11704-024-40452-4

Keywords