针对网络谣言溯源难度大,以信息载体模型和用户特征深度挖掘为切入点,提出了一种节点特征增强的溯源模型,旨在利用深度学习方法获取信息节点的高阶多尺度特征(高阶邻居、邻居状态、不同状态连接结构),并结合SEIR传播机制将节点状态学习为信息源(I态)与非信息源(S、E、R态)。首先,利用多种节点中心性指标扩充并丰富节点特征;其次,使用抗噪增强模块对扩充后的节点特征进行重构,并动态学习节点自身及其一阶邻居的特征;再次,使用度量学习方法调整节点特征空间,使得相同状态节点之间的距离缩小,以便区分节点的类别和特性;最后,将节点多维度特征融合并分类,最终确定信息源。实验结果表明,模型在模拟生成网络和实际网络上的信息溯源均取得相对较好的效果。
Aiming at the difficulty of tracing Internet rumors, a Node Feature-Enhanced Traceability Model (NFETM) is proposed based on information carrier model and in-depth mining of user characteristics. This paper aims to use deep learning method to obtain high-order multi-scale features of information nodes (high-order neighbors, neighbor states, different state connection structures), and combine SEIR propagation mechanism to learn node states into information sources (I states) and non-information sources (S, E, R states). Firstly, multiple node centrality indexes are used to expand and enrich node characteristics. Secondly, an anti-noise enhancement module is used to reconstruct the expanded node features, and dynamically learn the features of the node itself and its first-order neighbors. Thirdly, the metric learning method is used to adjust the node feature space, so that the distance between nodes in the same state is reduced, so as to distinguish the categories and characteristics of nodes. Finally, the multi-dimensional features of nodes are fused and classified to determine the information source. The experimental results show that the proposed model achieves relatively good results in both the simulated generation network and the real network.
[1] 于凯,白西柯,郭煜婕. 基于多中心性分析的网络舆情信息源点追溯研究[J].情报杂志, 2022, 41(3): 166-172.
YU K, BAI X K, GUO Y J. Traceability of network public opinion information sources based on multicentric analysis[J]. Journal of Intelligence, 2022, 41(3): 166-172.
[2] LI Z T, NIE W P, CAI S M, et al. Identifying important nodes in trip networks and investigating their determinants[J]. Entropy, 2023, 25(6): 958.
[3] 傅杰,邹艳丽,谢蓉. 结合网络动力学的电网关键节点识别[J]. 复杂系统与复杂性科学, 2017, 14(2): 31-38.
FU J, ZOU Y L, XIE R. Identification of critical nodes in a power network with considering the network dynamics[J]. Complex Systems and Complexity Science, 2017, 14(2): 31-38.
[4] 汪宏,鲍中奎,张海峰. 基于标签传播识别网络中的关键节点[J]. 复杂系统与复杂性科学, 2017, 14(2): 19-25.
WANG H, BAO Z K, ZHANG H F. Identifying influential nodes in complex networks based on the label spreading dynamics[J]. Complex Systems and Complexity Science, 2017, 14(2): 19-25.
[5] JIANG Y, MA H, LIU Y, et al. Enhancing social recommendation via two-level graph attentional networks[J]. Neurocomputing, 2021, 449: 71-84.
[6] HUANG J, LU T, ZHOU X, et al. HyperDNE: enhanced hypergraph neural network for dynamic network embedding[J]. Neurocomputing, 2023, 527: 155-166.
[7] KINGMA P D,WELLING M. Auto-encoding variational bayes[EB/OL]. (2013-12-20)[2023-08-11].https://doi.org/10.48550/arXiv.1312.6114.
[8] CRESWELL A, WHITE T, DUMOULIN V, et al. Generative adversarial networks: an overview[J]. IEEE Signal Processing Magazine, 2018, 35(1): 53-65.
[9] RADICCHI F, FORTUNATO S, MARKINES B, et al. Diffusion of scientific credits and the ranking of scientists[J]. Physical Review E, 2009, 80(5): 056103.
[10] PIOTR K R P T L.Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
[11] WATTS D J, STROGATZ S H. Collective dynamics of ‘small-world’ networks[J]. Nature, 1998, 393(6684): 440-442.
[12] BARABÁSI A L, ALBERT R. Emergence of scaling in random networks[J]. Science, 1999, 286(5439): 509-512.
[13] ERDÖS P, RÉNYI A. On the evolution of random graphs[J]. Publ Math Inst Hung Acad Sci, 1960, 5(1): 17-60.
[14] GUIMERA R, DANON L, DIAZ-GUILERA A, et al. Self-similar community structure in a network of human interactions[J]. Physical Review E, 2003, 68(6): 065103.
[15] NEWMAN M E J. Finding community structure in networks using the eigenvectors of matrices[J]. Physical Review E, 2006, 74(3): 036104.
[16] GEORGE R, SHUJAEE K, KERWAT M, et al. A comparative evaluation of community detection algorithms in social networks[J]. Procedia Computer Science, 2020, 171: 1157-1165.
[17] SHAH D, ZAMAN T. Rumors in a network: who's the culprit?[J]. IEEE Transactions on Information Theory, 2011, 57(8): 5163-5181.
[18] RESTREPO J G, OTT E, HUNT B R. Characterizing the dynamical importance of network nodes and links[J]. Physical Review Letters, 2006, 97(9): 094102.
[19] ZHU K, YING L. Information source detection in the SIR model: a sample-path-based approach[J]. IEEE/ACM Transactions on Networking, 2014, 24(1): 408-421.
[20] LI Q, SONG Y, JIN X Q. EG-PointNet: semantic segmentation for real point cloud scenes in challenging indoor environments[C].2022 16th ICME International Conference on Complex Medical Engineering (CME). China: Zhongshan: IEEE, 2022: 91-94.
[21] 徐冰冰,岑科廷,黄俊杰,等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5): 755-780.
XU B B, CEN K T, HUANG J J, et al. A Survey on graph convolutional neural network[J]. Chinese Journal of Computers, 2020, 43(5): 755-780.
[22] LIU J, ONG G P, CHEN X. GraphSAGE-based traffic speed forecasting for segment network with sparse data[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 23(3): 1755-1766.
[23] LAXMISAGAR H S, HANUMANTHARAJU M C. FPGA implementation of breast cancer detection using SVM linear classifier[J]. Multimedia Tools and Applications, 2023: 1-24.
[24] NOKERI T C, NOKERI T C. Back to the classics[DB/OL].[2022-12-20].https://doi.org/10.1007/978-1-4842-6870-4_9.
[25] 祝钧桃,姚光乐,张葛祥,等.深度神经网络的小样本学习综述[J]. 计算机工程与应用, 2021, 57(7): 22-33.
ZHU J T, YAO G L, ZHANG G X, et al. Survey of few shot learning of deep neural network[J]. Computer Engineering and Applications, 2021, 57(7): 22-33.
[26] KHAN S, NASEER M, HAYAT M, et al. Transformers in vision: a survey[J]. ACM Computing Surveys (CSUR), 2022, 54(10s): 1-41.
[27] 苏炯铭,刘鸿福,项凤涛等.深度神经网络解释方法综述[J]. 计算机工程, 2020, 46(9): 1-15.
SU J M,LIU H F,XIANG F T, et al. Survey of interpretation methods for deep neural networks[J]. Computer Engineering, 2020, 46(9): 1-15.
