Page 266 - 《软件学报》2026年第7期

岳立楠 等: 面向图分类任务的互补感知证据提取方法 2951

[36] Chen YQ, Bian YT, Han B, Cheng J. How interpretable are interpretable graph neural networks? In: Proc. of the 41st Int’l Conf. on
Machine Learning. PMLR, 2024. 6413–6456.
[37] Ribeiro MT, Singh S, Guestrin C. “Why should I trust you?”: Explaining the predictions of any classifier. In: Proc. of the 22nd ACM
SIGKDD Int’l Conf. on Knowledge Discovery and Data Mining. San Francisco: ACM, 2016. 1135–1144. [doi: 10.1145/2939672.
2939778]
[38] Li P, Song SH, Zhang Y, Cao HW, Ye XC, Tang ZM. HSEGRL: A hierarchical self-explainable graph representation learning model.
Journal of Computer Research and Development, 2024, 61(8): 1993–2007 (in Chinese with English abstract). [doi: 10.7544/issn1000-
1239.202440142]
[39] Wang YY, Zhang M, Yang JR, Xu SK, Chen YX. Research on fairness in deep learning models. Ruan Jian Xue Bao/Journal of Software,
2023, 34(9): 4037–4055 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6872.htm [doi: 10.13328/j.cnki.jos.006872]
[40] Yue LN, Liu Q, Du YC, An YQ, Wang L, Chen EH. DARE: Disentanglement-augmented rationale extraction. In: Proc. of the 36th Int’l
Conf. on Neural Information Processing Systems. New Orleans: Curran Associates Inc., 2022. 1929.
[41] Sun X, Wang L, Liu Q, Wu S, Wang ZL, Wang L. DIVE: Subgraph disagreement for graph out-of-distribution generalization. In: Proc. of
the 30th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining. Barcelona: ACM, 2024. 2794–2805. [doi: 10.1145/3637528.
3671878]
[42] Yang YH, Wu L, Liao YX, He ZZ, Shao PY, Hong RC, Wang M. Invariance matters: Empowering social recommendation via graph
invariant learning. In: Proc. of the 48th Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval. Padua: ACM,
2025. 2038–2047. [doi: 10.1145/3726302.3730013]
[43] Yue LN, Liu Q, Du YC, Wang L, An YQ, Chen EH. Towards reliable and faithful explanations: A disentanglement-augmented approach
for selective rationalization. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2025, 47(11): 9906–9921. [doi: 10.1109/TPAMI.
2025.3592313]
[44] Xu Z, Pan MH, Chen YZ, Chen HY, Yan YC, Das M, Tong HH. Fine-grained graph rationalization. In: Proc. of the 34th ACM Int’l
Conf. on Information and Knowledge Management. Seoul: ACM, 2025. 3708–3719. [doi: 10.1145/3746252.3761307]
[45] Piao YH, Lee S, Lu YJX, Kim S. Improving out-of-distribution generalization in graphs via hierarchical semantic environments. In: Proc.
of the 2024 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024. 27631–27640. [doi: 10.1109/
CVPR52733.2024.02609]
[46] Yao TJ, Chen YQ, Chen ZH, Hu K, Shen ZQ, Zhang K. Empowering graph invariance learning with deep spurious infomax. In: Proc. of
the 41st Int’l Conf. on Machine Learning. PMLR, 2024. 56860–56884.
[47] Jang E, Gu SX, Poole B. Categorical reparametrization with Gumble-Softmax. arXiv:1611.01144, 2016.
[48] Tishby N, Pereira FC, Bialek W. The information bottleneck method. arXiv:physics/0004057, 2000.
[49] Alemi AA, Fischer I, Dillon JV, Murphy K. Deep variational information bottleneck. In: Proc. of the 5th Int’l Conf. on Learning
Representations. Toulon: OpenReview.net, 2017.
[50] Pearl J, Glymour M, Jewell NP. Causal Inference in Statistics: A Primer. Chichester: John Wiley & Sons, 2016.
[51] Wang T, Huang JQ, Zhang HW, Sun QR. Visual commonsense R-CNN. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and
Pattern Recognition. Seattle: IEEE, 2020. 10760–10770. [doi: 10.1109/CVPR42600.2020.01077]
[52] Xu K, Hu W, Leskovec J, Jegelka S. How powerful are graph neural networks? In: Proc. of the 7th Int’l Conf. on Learning
Representations. New Orleans: OpenReview.net, 2019.
[53] Kingma DP, Ba J. Adam: A method for stochastic optimization. In: Proc. of the 3rd Int’l Conf. on Learning Representations. San Diego:
ICLR, 2015.
[54] Li QM, Han ZC, Wu XM. Deeper insights into graph convolutional networks for semi-supervised learning. In: Proc. of the 32nd AAAI
Conf. on Artificial Intelligence. New Orleans: AAAI Press, 2018. 433.

附中文参考文献
[26] 赵港, 王千阁, 姚烽, 张岩峰, 于戈. 大规模图神经网络系统综述. 软件学报, 2022, 33(1): 150–170. http://www.jos.org.cn/1000-9825/
6311.htm [doi: 10.13328/j.cnki.jos.006311]
[31] 周纯英, 曾诚, 何鹏, 张龑. GKCI: 改进的基于图神经网络的关键类识别方法. 软件学报, 2023, 34(6): 2509–2525. http://www.jos.org.
cn/1000-9825/6846.htm [doi: 10.13328/j.cnki.jos.006846]
[38] 李平, 宋舒寒, 张园, 曹华伟, 叶笑春, 唐志敏. HSEGRL: 一种分层可自解释的图表示学习模型. 计算机研究与发展, 2024, 61(8):
1993–2007. [doi: 10.7544/issn1000-1239.202440142]