Page 250 - 《软件学报》2026年第2期

于朋健 等: 面向节点分类的多层异质图神经网络 729

多关系局部信息聚合、高阶全局语义信息聚合和对比学习. MHGNN 学习节点在不同关系下的局部信息初始表
征, 再显式地探索不同关系下的表征的重要性, 并采用差异化的方式有效地融合不同类型节点的表征, 从而捕获了
不同关系下的交互信息. 此外, MHGNN 利用替代品和互补品矩阵来捕获不同关系下的高阶全局语义信息. 最后,
通过对比学习协调局部和全局两个视图的节点表征学习, 从而提高节点分类的性能. 在 6 个真实数据集上的实验
结果验证了所提出的 MHGNN 在节点分类任务上的优越性.

References
[1] Chen HX, Yin HZ, Wang WQ, Wang H, Nguyen QVH, Li X. PME: Projected metric embedding on heterogeneous networks for link
prediction. In: Proc. of the 24th ACM SIGKDD Int’l Conf. on Knowledge Discovery & Data Mining. London: ACM, 2018. 1177–1186.
[doi: 10.1145/3219819.3219986]
[2] Grover A, Leskovec J. node2vec: Scalable feature learning for networks. In: Proc. of the 22nd ACM SIGKDD Int’l Conf. on Knowledge
Discovery and Data Mining. San Francisco: ACM, 2016. 855–864. [doi: 10.1145/2939672.2939754]
[3] Fan HY, Zhang FB, Wei YX, Li ZY, Zou CQ, Gao Y, Dai QH. Heterogeneous hypergraph variational autoencoder for link prediction.
IEEE Trans. on Pattern Analysis and Machine Intelligence, 2022, 44(8): 4125–4138. [doi: 10.1109/TPAMI.2021.3059313]
[4] Jing BY, Park C, Tong HH. HDMI: High-order deep multiplex infomax. In: Proc. of the 2021 Web Conf. Ljubljana: ACM, 2021.
2414–2424. [doi: 10.1145/3442381.3449971]
[5] Xia LH, Huang C, Xu Y, Zhao JS, Yin DW, Huang J. Hypergraph contrastive collaborative filtering. In: Proc. of the 45th Int’l ACM
SIGIR Conf. on Research and Development in Information Retrieval. Madrid ACM, 2022. 70–79. [doi: 10.1145/3477495.3532058]
[6] Xue HS, Yang LW, Rajan V, Jiang W, Wei Y, Lin Y. Multiplex bipartite network embedding using dual hypergraph convolutional
networks. In: Proc. of the 2021 Web Conf. Ljubljana: ACM, 2021. 1649–1660. [doi: 10.1145/3442381.3449954]
[7] Ji HY, Wang X, Shi C, Wang B, Yu P. Heterogeneous graph propagation network. IEEE Trans. on Knowledge and Data Engineering,
2023, 35(1): 521–532. [doi: 10.1109/TKDE.2021.3079239]
[8] Park C, Kim D, Han JW, Yu H. Unsupervised attributed multiplex network embedding. In: Proc. of the 34th AAAI Conf. on Artificial
Intelligence. New York: AAAI Press, 2020. 5371–5378. [doi: 10.1609/aaai.v34i04.5985]
[9] Shi C, Hu BB, Zhao WX, Yu PS. Heterogeneous information network embedding for recommendation. IEEE Trans. on Knowledge and
Data Engineering, 2019, 31(2): 357–370. [doi: 10.1109/TKDE.2018.2833443]
[10] Xia LH, Xu Y, Huang C, Dai P, Bo LF. Graph meta network for multi-behavior recommendation. In: Proc. of the 44th Int’l ACM SIGIR
Conf. on Research and Development in Information Retrieval. ACM, 2021. 757–766. [doi: 10.1145/3404835.3462972]
[11] Wu F, Souza A, Zhang TY, Fifty C, Yu T, Weinberger K. Simplifying graph convolutional networks. In: Proc. of the 36th Int’l Conf. on
Machine Learning. 2019. 6861–6871.
[12] He L, Chen HX, Wang DX, Jameel S, Yu P, Xu GD. Click-through rate prediction with multi-modal hypergraphs. In: Proc. of the 30th
ACM Int’l Conf. on Information & Knowledge Management. ACM, 2021. 690–699. [doi: 10.1145/3459637.3482327]
[13] Liu ZJ, Huang C, Yu YW, Fan BD, Dong JY. Fast attributed multiplex heterogeneous network embedding. In: Proc. of the 29th ACM Int’l
Conf. on Information & Knowledge Management. ACM, 2020. 995–1004. [doi: 10.1145/3340531.3411944]
[14] Ying R, He RN, Chen KF, Eksombatchai P, Hamilton WL, Leskovec J. Graph convolutional neural networks for Web-scale
recommender systems. In: Proc. of the 24th ACM SIGKDD Int’l Conf. on Knowledge Discovery & Data Mining. London: ACM, 2018.
974–983. [doi: 10.1145/3219819.3219890]
[15] He XN, Deng K, Wang X, Li Y, Zhang YD, Wang M. LightGCN: Simplifying and powering graph convolution network for
recommendation. In: Proc. of the 43rd Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval. ACM, 2020.
639–648. [doi: 10.1145/3397271.3401063]
[16] Li WZ, Huang L, Wang CD, Ye YX. StarGAT: Star-shaped hierarchical graph attentional network for heterogeneous network
representation learning. In: Proc. of the 2021 IEEE Int’l Conf. on Data Mining (ICDM). Auckland: IEEE, 2021. 1198–1203. [doi: 10.1109/
ICDM51629.2021.00144]
[17] Tang J, Qu M, Wang MZ, Yan J, Mei QZ. LINE: Large-scale information network embedding. In: Proc. of the 24th Int’l Conf. on World
Wide Web. Florence: ACM, 2015. 1067–1077. [doi: 10.1145/2736277.2741093]
[18] Shi C, Wang RJ, Wang X. Survey on heterogeneous information networks analysis and applications. Ruan Jian Xue Bao/Journal of
Software, 2022, 33(2): 598–621 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6357.htm [doi: 10.13328/j.cnki.jos.
006357]
[19] Chen L, Wu L, Hong RC, Zhang K, Wang M. Revisiting graph based collaborative filtering: A linear residual graph convolutional