Attributed Bipartite Graph Neural Networks with Motifs Information for Network Representation Learning

doi:10.3778/j.issn.1002-8331.2301-0141

Abstract

Abstract: At present, network representation learning methods are mostly aimed at homogeneous networks, ignoring the particularity of attributed bipartite networks and the motifs structure of networks. In order to solve the above problems, this paper proposes an attributed bipartite graph neural network with motifs information for network representation learning (MABG). MABG adjusts the edge weights by the number of butterfly motifs formed by two nodes in the network, to construct the motifs weight matrix and obtain the attributed bipartite network adjacency matrix with motifs information. Then two different strategies are adopted to capture the explicit and implicit messages in the bipartite network. For explicit relationships, a message-passing mechanism is operated between different types of nodes. For implicit relationships, a message alignment mechanism is used in nodes of the same type. An adversarial model is implemented to minimize the difference between input attributes and explicit relationship representations. Finally, a cascaded framework is proposed to capture high-order network information and obtain the final node representation. Extensive experiments are conducted in recommended tasks on four real-world datasets. The results demonstrate the effectiveness of MABG compared with other state-of-art methods.

Key words: attributed bipartite network, network representation learning, network motifs, graph neural network

摘要： 目前网络表示学习方法大多针对通过网络，忽略了属性二分网络的特殊性以及网络的模体信息等。为了解决以上问题，提出一种保留模体信息的属性二分图神经网络表示学习方法MABG。该方法首先通过网络中两节点共同参与形成的蝶形模体数量来调整边的权重，从而构建模体权重矩阵，获得包含模体信息的属性二分网络邻接矩阵。接着采取不同的策略捕捉网络中的显式和属性隐式消息，对于不同类型节点集合间的显式关系采用消息传递机制，对于同类型节点中的隐式关系采用消息对齐机制，同时使用对抗模型最小化输入特征和显式关系表示之间的差异，之后通过级联框架来捕捉高阶信息并得到最终的节点表示。将该模型在四个真实公开的数据集上执行推荐任务并与其他方法进行对比，验证了该模型的有效性。

关键词: 属性二分网络, 网络表示学习, 网络模体, 图神经网络

LYU Shaoqing, WANG Chichi, LI Tingting, BAO Zhiqiang. Attributed Bipartite Graph Neural Networks with Motifs Information for Network Representation Learning[J]. Computer Engineering and Applications, 2024, 60(10): 148-155.

吕少卿, 王驰驰, 李婷婷, 包志强. 保留模体信息的属性二分图神经网络表示学习[J]. 计算机工程与应用, 2024, 60(10): 148-155.

References

[1] SHI Y, LEI M L, YANG H, et al. Diffusion network embedding[J]. Pattern Recognition, 2019, 88(2): 518-531.
[2] ZHANG D, YIN J, ZHU X, et al. Network representation learning: a survey[J]. IEEE Transactions on Big Data, 2018, 6(1): 3-28.
[3] CHEN J, WU Y, FAN L, et al. N2VSCDNNR: a local recommender system based on node2vec and rich information network[J]. IEEE Transactions on Computational Social Systems, 2019, 6(3): 456-466.
[4] XIE Y, YU B, LYU S Z, et al. A survey on heterogeneous network representation learning[J]. Pattern Recognition, 2021, 116(7): 107936.
[5] TISSOT H C. Novel perspectives and applications of knowledge graph embeddings: from link prediction to risk assessment and explain ability[C]//Proceedings of the 2021 International Conference on Research Challenges in Information Science. Cham: Springer, 2021: 91-106.
[6] PEROZZI B, AI-RFOU R, SKIENA S. DeepWalk: online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2014: 701-710.
[7] GROVER A, LESKOVER J. Node2vec: scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 855-864.
[8] TANG J, QU M, WANG M, et al. LINE: large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web. New York: ACM, 2015: 1067-1077.
[9] LIAO L Z, HE X N, ZHANG H W, et al. Attributed social network embedding[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(12): 2257-2270.
[10] AHMED H, ALI S. Research on bipartite network embedding with auxiliary information[C]//Proceedings of the 10th International Conference on Software Engineering and Service Science, Beijing, 2019: 1-6.
[11] 赵雪莉, 卢光跃, 吕少卿, 等. 结合属性信息的二分网络表示学习[J]. 计算机科学与探索, 2021, 15(3): 495-505.
ZHAO X L, LU G Y, LYU S Q, et al. Attributed bipartite network representation learning[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(3): 495-505.
[12] 李婷婷, 吕少卿, 赵雪莉, 等. 融合多层次结构信息的深度属性二分网络表示学习[J]. 计算机应用研究, 2021, 38(11): 3316-3321.
LI T T, LYU S Q, ZHAO X L, et al. Deep attributed bipartite network incorporating with multilevel structure information[J].Application Research of Computers, 2021, 38(11): 3316-3321.
[13] MILO R, SHEN-ORR S, ITZKOVITZ S, et al. Network motifs: simple building blocks of complex networks[J]. Science, 2002, 298(5594): 824-827.
[14] ZHANG F, BU T M. CN-Motifs perceptive graph neural networks[J]. IEEE Access, 2021, 9: 151285-151293.
[15] WANG L, REN J, XU B, et al. MODEL: motif-based deep feature learning for link prediction[J]. IEEE Transactions on Computational Social Systems, 2020, 7(2): 503-516.
[16] LI X, WEI W, FENG X, et al. Representation learning of graphs using graph convolutional multilayer networks based on motifs[J]. Neurocomputing, 2021, 464(5): 218-226.
[17] DAREDDY M R, DAS M, YANG H. Motif2vec: motif aware node representation learning for heterogeneous networks[C]//Proceedings of the 2019 IEEE International Conference on Big Data, 2019: 1052-1059.
[18] YU Y, LU Z, LIU J, et al. RUM: network representation learning using motifs[C]//Proceedings of the 35th IEEE International Conference on Data Engineering, 2019: 1382-1393.
[19] XIE T, HE C, REN X, et al. L-BGNN: layerwise trained bipartite graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(12): 10711-10723.
[20] XUE H, YANG L, RAJAN V, et al. Multiplex bipartite network embedding using dual hypergraph convolutional networks[C]//Proceedings of the Web Conference 2021, Slovenia, 2021: 1649-1660.
[21] YANG R, SHI J, HUANG K, et al. Scalable and effective bipartite network embedding[C]//Proceedings of the 2022 International Conference on Management of Data, 2022: 1977-1991.
[22] GAO M, HE X, CHEN L, et al. Learning vertex representations for bipartite networks[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(1): 379-393.
[23] CAO J, LIN X, GUO S, et al. Bipartite graph embedding via mutual information maximization[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 2021: 635-643.