RMFKAN：基于改进图Mamba的网络水军检测方法

doi:10.3778/j.issn.1673-9418.2407124

摘要/Abstract

摘要： 网络水军检测任务对构建和谐网络空间至关重要。针对现有基于图Transformer的网络水军检测方法无差别传递来自社区的节点之间的信息，从而导致节点表示过于同质，在处理长距离依赖关系时存在过度压缩和过度平滑，最终降低网络水军检测效果的问题，提出了一种基于关系双向图Mamba的傅里叶Kolmogorov-Arnold网络（RMFKAN）模型用于检测社交平台中的网络水军。通过异质感知的长距离关系特征提取方法解决了大规模社交网络跨社区长距离关系特征丢失的问题。通过引入双向选择状态空间模型（Bi-Mamba）解决了处理长距离依赖关系时的过度压缩和过度平滑问题。具体而言，通过随机游走策略令牌化子图，输入消息传递神经网络独立处理不同类型的边，利用傅里叶系数改进的KAN增强特征，将特征矩阵输入Bi-Mamba，提高对长距离依赖关系的捕捉能力，同时有效降低训练复杂度。在两个公开的网络水军检测数据集Twibot-20和Twibot-22上与10个基线模型进行对比实验，实验结果表明，RMFKAN在多个评价指标上均优于现有的基线方法，与现有研究的最佳效果相比RMFKAN的F1分数分别提高了2.10和4.06个百分点，准确率分别提高了1.01和4.45个百分点，验证了其在网络水军检测任务中的优越性能。

关键词: 网络水军检测, 图神经网络, 随机游走, Mamba

Abstract: Detecting network spammers is crucial for creating a harmonious online environment. Existing graph Transformer-based methods for network spammers detection face challenges due to indiscriminate information propagation between nodes within communities. This leads to overly homogeneous node representations and issues with excessive compression and smoothing when handling long-range dependencies, ultimately reducing the effectiveness of network spammers detection. A novel model, the relational bi-directional graph Mamba Fourier Kolmogorov-Arnold network (RMFKAN), is proposed to address these challenges in detecting network spammers on social platforms. The method of heterogeneous perception long-distance relationship feature extraction is used to solve the problem of feature loss in long-distance relationships across communities in large-scale social networks. The bi-directional selection state space model (Bi-Mamba) is introduced to address the issues of over-compression and over-smoothing when dealing with long-distance dependencies. Specifically, subgraphs are tokenized by the random walk strategy, message passing neural networks are input to independently handle different types of edges, and features are enhanced by KAN improved with Fourier coefficients. The feature matrix is input into Bi-Mamba to improve the ability of capturing long-distance dependencies and effectively reduce training complexity. On the two public online spammer detection datasets Twibot-20 and Twibot-22, compared with 10 baseline models, the experimental results show that RMFKAN is superior to existing baseline methods in multiple evaluation indicators. Compared with the best results of existing research, the F1 score of RMFKAN is increased by 2.10 and 4.06 percentage points respectively, and the accuracy is increased by 1.01 and 4.45 percentage points respectively, which verifies its superior performance in the task of network spammers detection.

Key words: network spammers detection, graph neural network, random walk, Mamba

王宇哲, 颜靖华, 卜凡亮, 王一帆, 李嘉, 韩竹轩. RMFKAN：基于改进图Mamba的网络水军检测方法[J]. 计算机科学与探索, 2025, 19(5): 1365-1378.

WANG Yuzhe, YAN Jinghua, BU Fanliang, WANG Yifan, LI Jia, HAN Zhuxuan. RMFKAN: Network Spammers Detection Method Based on Improved Graph Mamba[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(5): 1365-1378.

参考文献

[1] SCHONFELD A, MCNIEL D, TOYOSHIMA T, et al. Cyberbullying and adolescent suicide[J]. Journal of the American Academy of Psychiatry and the Law, 2023, 51(1): 112-119.
[2] 中国青年报.65.3%受访青年表示自己或周围人遭遇过网络暴力[EB/OL] (2023-06-20) [2024-06-12]. http://tech.youth. cn/wzlb/202306/t20230620_14596022.htm.
The China Youth Daily. 65.3% of youth said themselves or people around you faced violence[EB/OL] (2023-06-20) [2024-06-12]. http://http://tech.youth.cn/wzlb/202306/t20230620_14596022.htm.
[3] FERRARA E. Social bot detection in the age of ChatGPT: challenges and opportunities[J]. First Monday, 2023, 28(6).
[4] HIMELEIN-WACHOWIAK M, GIORGI S, DEVOTO A, et al. Bots and misinformation spread on social media: implications for COVID-19[J]. Journal of Medical Internet Research, 2021, 23(5): e26933.
[5] SHI W, LIU D Y, YANG J, et al. Social bots’ sentiment engagement in health emergencies: a topic-based analysis of the COVID-19 pandemic discussions on twitter[J]. International Journal of Environmental Research and Public Health, 2020, 17(22): 8701.
[6] DUKIC D, KECA D, STIPIC D. Are you human? Detecting bots on Twitter using BERT[C]//Proceedings of the 2020 IEEE 7th International Conference on Data Science and Advanced Analytics.. Piscataway: IEEE, 2020: 631-636.
[7] CRESCI S. A decade of social bot detection[J]. Communications of the ACM, 2020, 63(10): 72-83.
[8] 韩竹轩, 卜凡亮, 侯智文, 等. 改进KGAT的恐怖组织空间行为预测方法[J/OL]. 计算机科学与探索 [2024-07-10]. http://kns.cnki.net/kcms/detail/11.5602.tp.20240711.436.002. html.
HAN Z X, BU F L, HOU Z W, et al. Improved KGAT method for spatial behavior prediction of terrorist organizations[J/OL]. Journal of Frontiers of Computer Science and Technology [2024-07-15]. http://kns.cnki.net/kcms/detail/11.5602. tp.20240711.1436.002.html..
[9] BEHROUZ A, HASHEMI F. Graph Mamba: towards learning on graphs with state space models[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2024: 119-130.
[10] CHEN H Y, XU Z, YEH C M, et al. Masked graph transformer for large-scale recommendation[C]//Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2024: 2502-2506.
[11] SUN Y D, ZHU D J, WANG Y S, et al. SpikeGraphormer: a high-performance graph transformer with spiking graph attention[EB/OL]. [2024-07-15]. https://arxiv.org/abs/2403. 15480.
[12] HAMED S, AMEYA V, BALAJI V, et al. Exphormer: scaling graph transformers with expander graphs[C]//Proceedings of the 11th International Conference on Learning Representations, 2023.
[13] ALOTHALI E, ZAKI N, MOHAMED E A, et al. Detecting social bots on Twitter: a literature review[C]//Proceedings of the 2018 International Conference on Innovations in Information Technology. Piscataway: IEEE, 2018: 175-180.
[14] KUDUGUNTA S, FERRARA E. Deep neural networks for bot detection[J]. Information Sciences, 2018, 467: 312-322.
[15] MILLER Z, DICKINSON B, DEITRICK W, et al. Twitter spammer detection using data stream clustering[J]. Information Sciences, 2014, 260: 64-73.
[16] HAYAWI K, MATHEW S, VENUGOPAL N, et al. DeeProBot: a hybrid deep neural network model for social bot detection based on user profile data[J]. Social Network Analysis and Mining, 2022, 12(1): 43.
[17] WILLIAMS E M, NOVAK V, BLACKWELL D, et al. Homophily and transitivity in bot disinformation networks[C]//Proceedings of the 2020 7th International Conference on Social Networks Analysis, Management and Security. Piscataway: IEEE, 2020: 1-7.
[18] 姜钰棋, 侯智文, 王一帆, 等. 社交平台不平衡文本数据处理与应用研究[J]. 计算机科学与探索, 2024, 18(9): 2370-2383.
JIANG Y Q, HOU Z W, WANG Y F, et al. Research on processing and application of imbalanced textual data on social platforms[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(9): 2370-2383.
[19] 郭奕, 徐亮, 熊雪军. 社交网络中意见领袖挖掘方法综述[J]. 计算机科学与探索, 2021, 15(11): 2077-2092.
GUO Y, XU L, XIONG X J. Survey on methods of opinion leader mining in social networks[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(11): 2077-2092.
[20] ALI ALHOSSEINI S, BIN TAREAF R, NAJAFI P, et al. Detect me if you can: spam bot detection using inductive representation learning[C]//Proceedings of the 2019 World Wide Web Conference. New York: ACM, 2019: 148-153.
[21] FENG S B, WAN H R, WANG N N, et al. BotRGCN: Twitter bot detection with relational graph convolutional networks[C]//Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. New York: ACM, 2021: 236-239.
[22] GU A, DAO T. Mamba: linear-time sequence modeling with selective state spaces[EB/OL]. [2024-07-16]. https://arxiv.org/abs/2312.00752.
[23] MANZIL Z, GURU G, AVINAVA D, et al. Big bird: transformers for longer sequences[C]//Advances in Neural Information Processing Systems 33, 2020: 17283-17297.
[24] WANG S, LI B, KHABSA M, et al. Linformer: self-attention with linear complexity[EB/OL]. [2024-07-16]. https://arxiv.org/abs/2006.04768.
[25] LIU Z M, WANG Y X, VAIDYA S, et al. KAN: Kolmogorov-Arnold networks[EB/OL]. [2024-07-16]. https://arxiv.org/abs/2404.19756.
[26] GENET R, INZIRILLO H. TKAN: temporal Kolmogorov-Arnold networks[EB/OL]. [2024-07-18]. https://arxiv.org/abs/2405.07344.
[27] GENET R, INZIRILLO H. A temporal Kolmogorov-Arnold transformer for time series forecasting[EB/OL]. [2024-07-18]. https://arxiv.org/abs/2406.02486.
[28] FENG F L, HE X N, ZHANG H W, et al. Cross-GCN: enhancing graph convolutional network with K-order feature interactions[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1): 225-236.
[29] ZHU J, YAN Y J, ZHAO L X, et al. Beyond homophily in graph neural networks[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems. New York: ACM, 2020: 7793-7804.
[30] DEHGHAN A, SIUTA K, SKORUPKA A, et al. Detecting bots in social-networks using node and structural embeddings[J]. Journal of Big Data, 2023, 10(1): 119.
[31] ZHOU M, FENG W Z, ZHU Y F, et al. Semi-supervised social bot detection with initial residual relation attention networks[C]//Proceedings of the 2023 European Conference on Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track. Cham: Springer, 2023: 207-224.
[32] FENG S B, WAN H R, WANG N N, et al. TwiBot-20: a comprehensive Twitter bot detection benchmark[C]//Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York: ACM, 2021: 4485-4494.
[33] FENG S B, TAN Z X, WAN H R, et al. TwiBot-22: towards graph-based twitter bot detection[EB/OL]. [2014-07-18]. https://arxiv.org/abs/2206.04564.
[34] MEIROM E, MARON H, MANNOR S, et al. Controlling graph dynamics with reinforcement learning and graph neural networks[C]//Proceedings of the 38th International Conference on Machine Learning, 2021: 7565-7577.
[35] ZHANG M, SAAB K K, POLI M, et al. Effectively modeling time series with simple discrete state spaces[EB/OL]. [2024-07-18]. https://arxiv.org/abs/2303.09489.
[36] FONSECA ABREU J V, GHEDINI RALHA C, COSTA GONDIM J J. Twitter bot detection with reduced feature set[C]//Proceedings of the 2020 IEEE International Conference on Intelligence and Security Informatics. Piscataway: IEEE, 2020: 1-6.
[37] LIU Y H, OTT M, GOYAL N, et al. RoBERTa: a robustly optimized BERT pretraining approach[EB/OL]. [2024-07-18]. https://arxiv.org/abs/1907.11692.
[38] LV Q S, DING M, LIU Q, et al. Are we really making much progress? Revisiting, benchmarking and refining heterogeneous graph neural networks[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York: ACM, 2021: 1150-1160.
[39] YANG K-C, VAROL O, HUI P-M, et al. Scalable and generalizable social bot detection through data selection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 1096-1103.
[40] FENG S B, TAN Z X, LI R, et al. Heterogeneity-aware Twitter bot detection with relational graph transformers[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(4): 3977-3985.
[41] LIU Y H, TAN Z X, WANG H, et al. BotMoE: Twitter bot detection with community-aware mixtures of modal-specific experts[C]//Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2023: 485-495.