属性多路异构网络的哈希表示方法

doi:10.3778/j.issn.1002-8331.2406-0061

摘要/Abstract

摘要： 异构网络在诸多领域中得到广泛应用和研究，然而，现有的网络表示方法在处理异构网络时常常遇到挑战。其中之一是未充分利用节点属性信息，导致表示结果缺乏表征力。另一个挑战是网络结构的复杂性，使得现有表示方法往往无法捕捉到网络的重要特征，从而影响了下游任务的效果。属性多路异构网络的哈希表示方法旨在解决上述问题。该方法通过将节点的属性特征和网络结构信息整合到节点表示中，采用深度哈希层来学习节点的紧凑表示，从而获得网络的哈希表示。与传统的表示方法相比，该方法能够更好地保留节点的重要属性特征，并且通过哈希技术将节点表示压缩为固定长度的二进制编码，提高了表示的效率和可扩展性。充分的实验结果表明，属性多路异构网络的哈希表示方法能够在保持表示质量的同时大幅降低表示的维度，从而为后续的下游任务提供了更加高效的网络表示。

关键词: 网络表示, 异构网络, 深度哈希, 属性多路异构网络

Abstract: Heterogeneous networks have been widely utilized in many fields. However, existing network embedding methods often meet challenges when dealing with heterogeneous networks. One of them is the underutilization of node attribute information, resulting in a lack of representational power. Another challenge is the complexity of the network structure, which makes existing representations often unable to capture important features of the network, thus affecting the effect of downstream tasks. The hash embedding for attributed multiplex heterogeneous network (AMHEN) aims to solve the above problems. By integrating the attributes of nodes and the network structure information into the node embedding, the method uses the deep hash layer to learn the compact representation of nodes, so as to obtain the hash embedding. Compared with the traditional embedding method, the proposed method can better retain the important attributes of nodes, and compress the node representation into fixed length binary coding by hash technology, which improves the efficiency and scalability of the embedding. Sufficient experimental results show that the proposed hash embedding for AMHEN can significantly reduce the embedding dimension while maintaining the embedding quality, thus providing a more efficient network embedding for subsequent downstream tasks.

Key words: network embedding, heterogeneous network, deep hash, attributed multiplex heterogeneous network

苏惠敏, 李倩, 郭红钰, 刘玉龙. 属性多路异构网络的哈希表示方法[J]. 计算机工程与应用, 2024, 60(24): 131-139.

SU Huimin, LI Qian, GUO Hongyu, LIU Yulong. Hash Embedding for Attributed Multiplex Heterogeneous Network[J]. Computer Engineering and Applications, 2024, 60(24): 131-139.

参考文献

[1] KHOSHRAFTAR S, AN A J. A survey on graph representation learning methods[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 15(1): 1-55.
[2] CUI P, WANG X, PEI J, et al. A survey on network embedding[J]. IEEE Transactions on Knowledge & Data Engineering, 2019, 31(5): 833-852.
[3] 蹇松雷, 卢凯. 复杂异构数据的表征学习综述[J]. 计算机科学, 2020, 47(2): 1-9.
JIAN S L, LU K. Survey on representation learning of complex heterogeneous data[J]. Computer Science, 2020, 47(2): 1-9.
[4] CEN Y, ZOU X, ZHANG J, et al. Representation learning for attributed multiplex heterogeneous network[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD’19), 2019.
[5] 欧明栋. 面向大规模异构数据的哈希表征学习研究[D]. 北京: 清华大学, 2016.
OU M D. Hashing representation learning for massive heterogeneous data[D]. Beijing: Tsinghua University, 2016.
[6] LIU Z, HUANG C, YU Y, et al. Fast attributed multiplex heterogeneous network embedding[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management (CIKM’20), 2020.
[7] PARK C, KIM D, HAN J, et al. Unsupervised attributed multiplex network embedding[J]. arXiv:1911.06750, 2019.
[8] LUO X, WANG H, WU D, et al. A survey on deep hashing methods[J]. ACM Transactions on Knowledge Discovery from Data, 2023, 17(1): 1-50.
[9] PEROZZI B, AL-RFOU R, SKIENA S S. Deepwalk: online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’14), 2014.
[10] GROVER A, LESKOVEC J. node2vec: scalable feature learning for networks[J]. arXiv:1607.00653, 2016.
[11] 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 (WWW’15), 2015.
[12] QIU J, DONG Y, MA H, et al. Network embedding as matrix factorization: unifying DeepWalk, LINE, PTE, and node2vec[C]//Proceedings of the 11th ACM International Conference on Web Search and Data Mining, 2018.
[13] KIPF T, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[14] SCHLICHTKRULL M, KIPF T, BLOEM P, et al. Modeling relational data with graph convolutional networks[J]. arXiv:1703.06103v4, 2017.
[15] HAMILTON W L, YING Z, LESKOVEC J. Inductive representation learning on large graphs[J]. arXiv:1706.02216, 2017.
[16] DONG Y, NITESH V C, ANANTHRAM S. metapath2vec: scalable representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’17), 2017.
[17] SHI C, HU B, ZHAO W, et al. Heterogeneous information network embedding for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(2): 357-370.
[18] TANG J, QU M, MEI Q. PTE: predictive text embedding through large-scale heterogeneous text networks[C]//Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’15), 2015.
[19] ZHANG C, SONG D, HUANG C, et al. Heterogeneous graph neural network[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’19), 2019.
[20] HU B, FANG Y, SHI C. Adversarial learning on heterogeneous information networks[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’19), 2019.
[21] YAO W, LI H Z. Heterogeneous attributed network embedding with graph convolutional networks[C]//Proceedings of the 2021 International Conference on Communications, Information System and Computer Engineering, 2021.
[22] ZHANG H, QIU L, YI L, et al. Scalable multiplex network embedding[C]//Proceedings of the International Joint Conference on Artificial Intelligence, 2018.
[23] LIU W Y, CHEN P Y, YEUNG S, et al. Principled multilayer network embedding[C]//Proceedings of the 2017 IEEE International Conference on Data Mining Workshops (ICDMW), 2017.
[24] QU M, TANG J, SHANG J, et al. An attention-based collaboration framework for multi-view network representation learning[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM’17), 2017: 1767-1776.
[25] SHI Y, HAN F, HE X R, et al. mvn2vec: preservation and collaboration in multi-view network embedding[J]. arXiv:1801.06597, 2018.
[26] YU P, FU C, YU Y, et al. Multiplex heterogeneous graph convolutional network[C]//Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’22), 2022.
[27] FU C, YU P, YU Y, et al. MHGCN+: multiplex heterogeneous graph convolutional network[J]. ACM Transactions on Intelligent Systems and Technology, 2024, 15(3): 1-25.
[28] 吕少卿, 王驰驰, 李婷婷, 等. 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.
LYU S Q, WANG C C, LI T T, et al. Attributed bipartite graph neural networks with motifs information for network representation learning[J]. Computer Engineering and Applications, 2024, 60(10): 148-155.
[29] YANG H, PAN S, ZHANG P, et al. Binarized attributed network embedding[C]//Proceedings of the IEEE International Conference on Data Mining (ICDM), 2018.
[30] YANG H, PAN S, CHEN L, et al. Low-bit quantization for attributed network representation learning[C]//Proceedings of the International Joint Conference on Artificial Intelligence, 2020.
[31] WU W, LI B, CHEN L, et al. Efficient attributed network embedding via recursive randomized hashing[C]//Proceedings of the International Joint Conference on Artificial Intelligenc, 2018.
[32] WU W, LI B, LUO C, et al. Hashing-accelerated graph neural networks for link prediction[C]//Proceedings of the International Conference of World Wide Web, 2021.
[33] LEI T, JIN W G, BARZILAY R, et al. Deriving neural architectures from sequence and graph kernels[C]//Proceedings of the 34th International Conference on Machine Learning, 2017.
[34] WU W, LI B, LUO C, et al. MPSketch: message passing networks via randomized hashing for efficient attributed network embedding[J]. IEEE Transactions on Cybernetics, 2023, 54(5): 1-14.