Abstract：Aiming at the problem of missing node attributes in graph data, we proposes a novel attribute missing graph learning framework. The framework maps node attributes to edge attributes by reconstructing the structural joint bipartite network. This enables attribute completion and graph tasks to be performed together under a unified framework that can handle both continuous and discrete missing data. According to the attribute homogeneity and structural homogeneity of the attribute graph, we propose an attribute missing representation learning method, which introduces edge embeddings and attention mechanisms to capture the correlations between attribute-attribute and structure-attribute in structural joint bipartite network to enhance the missing attribute learning. Experimental results on four real-world datasets show that our framework outperforms the baselines in both attribute completion tasks, validating the effectiveness of the method.
韩忠明, 张舒群, 刘燕, 胡启文, 杨伟杰. 基于二部联合网络的属性缺失图学习方法[J]. 复杂系统与复杂性科学, 2025, 22(2): 55-63.
HAN Zhongming, ZHANG Shuqun, LIU Yan, HU Qiwen, YANG Weijie. Attribute Missing Graph Learning Method Based on the Structural Joint Bipartite Network[J]. Complex Systems and Complexity Science, 2025, 22(2): 55-63.
[1] TRAUD A L, MUCHA P J, PORTER M A. Social structure of Facebook networks[J]. Physica A, 2012, 391(16): 41654180. [2] 王玉,许楠楠,胡海波. 社交媒体中的跨平台信息扩散特征及机制[J]. 复杂系统与复杂性科学, 2022, 19(4): 716. WANG Y, XU N N, HU H B, Characteristics and mechanisms of cross-platform information diffusion in social media[J]. Complex Systems and Complexity Science, 2022, 19(4): 716. [3] YANG S, ZHANG Z, ZHOU J, et al. Financial risk analysis for SMEs with graph-based supply chain mining[C]//International Joint Conferences on Artificial Intelligence. Freiburg: IJCAI, 2021: 46614667. [4] 路冠平,李江平. 基于复杂网络演化模型的新冠危机对经济的冲击研究[J]. 复杂系统与复杂性科学,2023,20(1): 3440,65. LU G P, LI J P. Evolution model the economic lmpact of COVlD19 crisis based on complex network[J]. Complex Systems and Complexity Science, 2023,20(1): 3440,65. [5] GAINZA P, SVERRISSON F, MONTI F, et al. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning[J]. Nature Methods, 2020, 17: 184192. [6] 赵文炎,钟诚,田殿雄,等. 基于混合卷积神经网络特征增强的目标识别算法[DB/OL].[20250122]. http://kns.cnki.net/kcms/detail/37.1402.N.20241112.1140.002.html. ZHAO W Y, ZHONG C, TIAN D X, et al. Target recognition algorithm based on hybrid convolutional neura network feature enhancement[DB/OL].[20250122]. http://kns.cnki.net/kcms/detail/37.1402.N.20241112.1140.002.html. [7] 吴越, 王英, 王鑫, 等. 基于超图卷积的异质网络半监督节点分类[J]. 计算机学报, 2021, 44(11): 22482260. WU Y, WANG Y, WANG X, et al. Motif-based hypergraph convolution network for semi-supervised node classification on heterogeneous graph[J]. Chinese Journal of Computers, 2021, 44(11): 22482260. [8] WANG R, MOU S, WANG X, et al. Graph structure estimation neural networks[C]//The International Conference of World Wide Web. New York: ACM, 2021: 342353. [9] LIU X, ZHU X, LI M, et al. Multiple kernel k-means with incomplete kernels[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42(5): 11911204. [10] YOON J, JORDON J, SCHAAR M. GAIN: Missing data imputation using generative adversarial nets[C]//International conference on machine learning. New York: ACM, 2018: 56895698. [11] KINGMA D P, WELLING M. Auto-encoding variational Bayes[C]//International Conference on Learning Representations. Washington DC: ICLR, 2014. [12] TAGUCHI H, LIU X, MURATA T. Graph convolutional networks for graphs containing missing features[J]. Future Generation Computer Systems, 2021, 117: 155168. [13] HUANG X, SONG Q, LI Y, et al. Graph recurrent networks with attributed random walks[C]//ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York:ACM, 2019: 732740. [14] BURGETTE L F, REITER J P. Multiple imputation for missing data via sequential regression trees[J]. American Journal of Epidemiology, 2010, 172: 10701076. [15] KIM K Y, KIM B J, YI G S. Reuse of imputed data in microarray analysis increases imputation efficiency[J]. Bmc Bioinformatics, 2004, 5: 19. [16] HASTIE T, MAZUMDER R, LEE J D, et al. Matrix completion and low-rank SVD via fast alternating least squares[J]. The Journal of Machine Learning Research, 2015, 16(1): 33673402. [17] STEKHOVEN D J, BUHLMANN P. MissForest—non-parametric missing value imputation for mixed-type data[J]. Bmc Bioinformatics, 2012, 28(1): 112118. [18] SPINELLI I, SCARDAPANE S, UNCINI A. Missing data imputation with adversarially-trained graph convolutional networks[J]. Neural Networks, 2020, 129: 249260. [19] YOU J, MA X, DING Y, et al. Handling missing data with graph representation learning[J]. Advances in Neural Information Processing Systems, 2020, 33: 1907519087. [20] JIANG B, ZHANG Z. Incomplete graph representation and learning via partial graph neural networks[DB/OL].[20250122]. https://doi.org/10.48550/arXiv.2003.10130. [21] ROSSI E, KENLAY H, GORINOVA M I, et al. On the unreasonable effectiveness of feature propagation in learning on graphs with missing node features[DB/OL].[20241220]. https://arxiv.org/pdf/2111.12128. [22] BI W, XU B, SUN X, et al. Predicting the silent majority on graphs: knowledge transferable graph neural network[C]//The International Conference of World Wide Web. New York: ACM, 2023: 274285. [23] JIANG X, QIN Z, XU J, et al. Incomplete graph learning via attribute-structure decoupled variational auto-encoder[C]//ACM International Conference on Web Search and Data Mining. New York: ACM, 2024:9. [24] XIA R, ZHANG C, LI A, et al. Attribute imputation autoencoders for attribute-missing graphs[J]. Knowledge-Based Systems, 2024,291: 111583. [25] TU W, XIAO B, LIU X, et al. Revisiting initializing then refining: an incomplete and missing graph imputation network[J]. IEEE transactions on Neural Networks and Learning Systems, 2024, 36(2): 32443257. [26] BOJCHEVSKI A, SHCHUR O, ZUGNER D, et al. Netgan: generating graphs via random walks[C]//International Conference on Machine Learning. New York: ICML, 2018: 610619. [27] ZHANG M, CHEN Y. Inductive matrix completion based on graph neural networks[C]//International Conference on Learning Representations. Washington DC: ICLR, 2019. [28] RONG Y, HUANG W, XU T, et al. Dropedge: towards deep graph convolutional networks on node classification[C]//International Conference on Learning Representations. Washington DC: ICLR, 2020. [29] DAI E, WANG S. Say no to the discrimination: learning fair graph neural networks with limited sensitive attribute information[C]//ACM International Conference on Web Search and Data Mining. New York: ACM, 2021: 680688. [30] SIMSEK O, JENSEN D. Navigating networks by using homophily and degree[J]. Proceedings of the National Academy of Sciences of the United States of America, 2008, 105(35): 1275812762. [31] YANG L, LUO L, XIN L,et al. DAGNN: demand-aware graph neural networks for session-based recommendation[C]//ACM Special Interest Group on Information Retrieval. New York: ACM, 2022. [32] XU K, LI C, TIAN Y, et al. Representation learning on graphs with jumping knowledge networks[C]//International Conference on Machine Learning. Washington DC: ICLR, 2018.
