Social bot detection framework fusing multi-scale wavelet enhancement and self-supervised learning

doi:10.11772/j.issn.1001-9081.2025060744

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (6): 1756-1766.DOI: 10.11772/j.issn.1001-9081.2025060744

• Artificial intelligence • Previous Articles

Social bot detection framework fusing multi-scale wavelet enhancement and self-supervised learning

Yu CHEN¹, Shuaikang QI¹(), Liwei XU²(), Haotian ZHU¹

^1.College of Computer and Control Engineering，Northeast Forestry University，Harbin Heilongjiang 150040，China
^2.School of Management Science and Engineering，Dongbei University of Finance and Economics，Dalin Liaoning 116025，China

Received:2025-07-08 Revised:2025-09-10 Accepted:2025-09-18 Online:2025-10-16 Published:2026-06-10
Contact: Shuaikang QI, Liwei XU
About author:CHEN Yu， born in 1975， Ph. D.， associate professor. His research interests include machine learning， natural language processing， computational biology， image processing.
ZHU Haotian， born in 1999， M. S. candidate. His research interests include social network detection.
First author contact:QI Shuaikang， born in 1996， M. S. candidate. His research interests include social network.
XU Liwei， born in 1989， Ph. D.， associate professor. Her research interests include human-computer interaction， machine learning.
Supported by:
National Natural Science Foundation of China(72301060);Liaoning Provincial Social Security Research Project(LNSHAQ2025B016);Basic Research Project of Educational Department of Liaoning Province(JYTMS20230666)

融合多尺度小波增强与自监督学习的社交机器人检测框架

陈宇¹, 戚帅康¹(), 许莉薇²(), 朱浩天¹

^1.东北林业大学计算机与控制工程学院，哈尔滨 150040
^2.东北财经大学管理科学与工程学院，辽宁大连 116025

通讯作者: 戚帅康,许莉薇
作者简介:陈宇（1975—），男，黑龙江哈尔滨人，副教授，博士，CCF会员，主要研究方向：机器学习、自然语言处理、计算生物学、图像处理
朱浩天（1999—），男，山东滕州人，硕士研究生，主要研究方向：社交网络检测。
第一联系人：戚帅康（1996—），男，河南驻马店人，硕士研究生，主要研究方向：社交网络
许莉薇（1989—），女，辽宁大连人，副教授，博士，主要研究方向：人机交互、机器学习
基金资助:
国家自然科学基金资助项目(72301060);辽宁省社会安全研究项目(LNSHAQ2025B016);辽宁省教育厅基础科研项目(JYTMS20230666)

Abstract

Abstract:

To address the limitations of the existing social bot detection methods in multimodal feature modeling， disguised behavior recognition， and generalization under weakly supervised scenarios， a social bot detection framework fusing multi-scale wavelet enhancement and self-supervised learning， named W2A-BotNet （Wavelet-to-Attention Bot Network）， was proposed. In the framework， a unified three-channel representation of textual semantics， user attributes， and social relations was constructed to alleviate modality conflicts； a Multi-scale Attention Wavelet Neural Operator Block （MAWNOBlock） was designed to perform time-frequency decomposition of behavioral sequences， thereby capturing both periodic patterns and abrupt anomalies； a multi-source collaborative fusion mechanism was introduced to achieve dynamic semantic alignment through cross-modal interactions and gating； a self-supervised pretraining based on follower count distribution was incorporated to enhance feature representation under limited labeled data. Experimental results show that the accuracy of the W2A-BotNet is improved by 0.35， 4.86， and 2.21 percentage points respectively compared to the suboptimal methods on Cresci-15， Cresci-17， and TwiBot-20 datasets， respectively. It can be seen that W2A-BotNet enhances the identification of bot accounts on social platforms effectively and provides a generalized detection framework for social network security governance.

Key words: social bot detection, self-supervised learning, wavelet transformation, user representation learning, machine learning, neural network

摘要：

针对现有社交机器人检测方法多模态特征建模不足、伪装行为难以识别及弱监督场景下泛化性欠缺的问题，提出一种融合多尺度小波增强与自监督学习的社交机器人检测框架——W2A-BotNet （Wavelet-to-Attention Bot Network）。该框架对文本语义、用户属性和社交关系构建统一的三通道表示，以缓解模态冲突；设计多尺度注意力小波神经算子模块（MAWNOBlock）对行为序列进行时频分解，捕捉周期规律与突发异常；提出多源协同融合机制，通过跨模态交互与门控实现动态语义对齐；引入基于粉丝数分布的自监督预训练，在少量标注数据的条件下加强特征表征。实验结果表明，W2A-BotNet的准确率在Cresci-15、Cresci-17与TwiBot-20数据集上相较于次优方法分别提高了0.35、4.86和2.21个百分点。可见，W2A-BotNet可有效提升社交平台上对机器人账户的识别能力，为社交网络的安全治理提供了可推广的检测框架。

关键词: 社交机器人检测, 自监督学习, 小波变换, 用户表示学习, 机器学习, 神经网络

CLC Number:

TP309

Yu CHEN, Shuaikang QI, Liwei XU, Haotian ZHU. Social bot detection framework fusing multi-scale wavelet enhancement and self-supervised learning[J]. Journal of Computer Applications, 2026, 46(6): 1756-1766.

陈宇, 戚帅康, 许莉薇, 朱浩天. 融合多尺度小波增强与自监督学习的社交机器人检测框架[J]. 《计算机应用》唯一官方网站, 2026, 46(6): 1756-1766.

Figures/Tables 11

References 62

[1]	CRESCI S. A decade of social bot detection［J］. Communications of the ACM， 2020， 63（10）： 72-83.
[2]	杨舟. 社交网络机器人检测综述［J］. 网络安全技术与应用. 2022（3）： 135-136.
	YANG Z. Overview of social network bot detection［J］. Network Security Technology and Application， 2022（3）： 135-136.
[3]	周钰颖，闵勇，江婷君，等. 社交媒体机器人的研究现状、挑战与展望［J］. 小型微型计算机系统， 2022， 43（10）： 2113-2121.
	ZHOU Y Y， MIN Y， JIANG T J， et al. Research status， challenges， and prospects of social media bots［J］. Journal of Chinese Computer Systems， 2022， 43（10）： 2113-2121.
[4]	FERRARA E， VAROL O， DAVIS C， et al. The rise of social bots［J］. Communications of the ACM， 2016， 59（7）： 96-104.
[5]	BRONIATOWSKI D A， JAMISON A M， QI S， et al. Weaponized health communication： Twitter bots and Russian trolls amplify the vaccine debate［J］. American Journal of Public Health， 2018， 108（10）： 1378-1384.
[6]	KOGAN S， MOSKOWITZ T J， NIESSNER M. Social media and financial news manipulation ［J］. Review of Finance， 2023， 27（4）： 1229-1268.
[7]	SHAO C， CIAMPAGLIA G L， VAROL O， et al. The spread of fake news by social bots［EB/OL］. ［2025-04-23］..
[8]	YANG K C， VAROL O， HUI P M， et al. Scalable and generalizable social bot detection through data selection［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2020： 1096-1103.
[9]	FERRARA E. Social bot detection in the age of ChatGPT： challenges and opportunities［J］. First Monday， 2023， 28（6）： No.13185.
[10]	DAVIS C A， VAROL O， FERRARA E， et al. BotOrNot： a system to evaluate social bots［C］// Proceedings of the 25th International Conference Companion on World Wide Web. Republic and Canton of Geneva： International World Wide Web Conferences Steering Committee， 2016： 273-274.
[11]	CRESCI S， PETROCCHI M， SPOGNARDI A， et al. From reaction to proaction： unexplored ways to the detection of evolving spambots［C］// Companion Proceedings of the Web Conference 2018. Republic and Canton of Geneva： International World Wide Web Conferences Steering Committee， 2018： 1469-1470.
[12]	REN L， HU R， LI D， et al. Dynamic graph neural network-based fraud detectors against collaborative fraudsters［J］. Knowledge-Based Systems， 2023， 278： No.110888.
[13]	FAZIL M， SAH A K， ABULAISH M. DeepSBD： a deep neural network model with attention mechanism for SocialBot detection［J］. IEEE Transactions on Information Forensics and Security， 2021， 16： 4211-4223.
[14]	ZHANG D S. Wavelet transform［M］// Fundamentals of image data mining： analysis， features， classification and retrieval， TCS. Cham： Springer， 2021： 45-54.
[15]	CORDONNIER J B， LOUKAS A， JAGGI M. Multi-head attention： collaborate instead of concatenate［EB/OL］. ［2025-04-23］..
[16]	CHU Z， GIANVECCHIO S， WANG H， et al. Who is tweeting on Twitter： human， bot， or cyborg？［C］// Proceedings of the 26th Annual Computer Security Applications Conference. New York： ACM， 2010： 21-30.
[17]	LEE K， CAVERLEE J， WEBB S. The social honeypot project： protecting online communities from spammers［C］// Proceedings of the 19th International Conference on World Wide Web. New York： ACM， 2010： 1139-1140.
[18]	RATKIEWICZ J， CONOVER M， MEISS M， et al. Truthy： mapping the spread of astroturf in microblog streams［C］// Proceedings of the 20th International Conference Companion on World Wide Web. New York： ACM， 2011： 249-252.
[19]	BENEVENUTO F， MAGNO G， RODRIGUES T， et al. Detecting spammers on Twitter ［EB/OL］. ［2025-04-23］..
[20]	CHANG H C H， FERRARA E. Comparative analysis of social bots and humans during the COVID-19 pandemic［J］. Journal of Computational Social Science， 2022， 5（2）： 1409-1425.
[21]	SUBRAHMANIAN V S， AZARIA A， DURST S， et al. The DARPA Twitter bot challenge［J］. Computer， 2016， 49（6）： 38-46.
[22]	ARIN E， KUTLU M. Deep learning based social bot detection on Twitter［J］. IEEE Transactions on Information Forensics and Security. 2023， 18： 1763-1772.
[23]	ELLAKY Z， BENABBOU F， OUAHABI S. Systematic literature review of social media bots detection systems ［J］. Journal of King Saud University — Computer and Information Sciences， 2023， 35（5）： No.101551.
[24]	CAI C， LI L， ZENG D. Detecting social bots by jointly modeling deep behavior and content information［C］// Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York： ACM， 2017： 1995-1998.
[25]	WANDA P， JIE H J. DeepProfile： finding fake profile in online social network using dynamic CNN［J］. Journal of Information Security and Applications， 2020， 52： No.102465.
[26]	PING H， QIN S. A social bots detection model based on deep learning algorithm［C］// Proceedings of the IEEE 18th International Conference on Communication Technology. Piscataway： IEEE， 2018： 1435-1439.
[27]	HAJLI N， SAEED U， TAJVIDI M， et al. Social bots and the spread of disinformation in social media： the challenges of artificial intelligence［J］. British Journal of Management， 2022， 33（3）： 1238-1253.
[28]	WANG S， CAO J， YU P S. Deep learning for spatio-temporal data mining： a survey［J］. IEEE Transactions on Knowledge and Data Engineering， 2022， 34（8）： 3681-3700.
[29]	DEVLIN J， CHANG M W， LEE K， et al. BERT： pre-training of deep bidirectional Transformers for language understanding［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies， Volume 1 （Long and Short Papers）. Stroudsburg： ACL， 2019： 4171-4186.
[30]	RADFORD A， NARASIMHAN K， SALIMANS T， et al. Improving language understanding by generative pre-training ［EB/OL］. ［2025-04-23］..
[31]	LEI Z， WAN H， ZHANG W， et al. BIC： Twitter bot detection with text-graph interaction and semantic consistency［C］// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg： ACL， 2023： 10326-10340.
[32]	FENG S， TAN Z， WAN H， et al. TwiBot-22： towards graph-based Twitter bot detection［C］// Proceedings of the 36th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2022： 35254-35269.
[33]	PENG H， ZHANG J Y， HUANG X， et al. Unsupervised social bot detection via structural information theory［J］. ACM Transactions on Information Systems. 2024， 42（6）： No.148.
[34]	ZHAO J， LIU X D， YAN Q B， et al. Multi-attributed heterogeneous graph convolutional network for bot detection［J］. Information Sciences， 2020， 537： 380-393.
[35]	LIU F， YANG C， LI Z， et al. Accou2vec： a social bot detection model based on community walk［J］. IEEE Transactions on Dependable and Secure Computing， 2026， 23（2）： 1751-1766.
[36]	HENDRYCKS D， MAZEIKA M， KADAVATH S， et al. Using self-supervised learning can improve model robustness and uncertainty［C］// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2019： 15663-15674.
[37]	SIRIWARDHANA S， KALUARACHCHI T， BILLINGHURST M， et al. Multimodal emotion recognition with Transformer-based self supervised feature fusion［J］. IEEE Access， 2020， 8： 176274-176285.
[38]	IDHAMMAD M， AFDEL K， BELOUCH M. Semi-supervised machine learning approach for DDoS detection［J］. Applied Intelligence， 2018， 48（10）： 3193-3208.
[39]	ECKARDT J N， BORNHÄUSER M， WENDT K， et al. Semi-supervised learning in cancer diagnostics［J］. Frontiers in Oncology， 2022， 12： No.960984.
[40]	KARISANI P， KARISANI N. Semi-supervised text classification via self-pretraining［C］// Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York： ACM， 2021： 40-48.
[41]	SONG Z， YANG X， XU Z， et al. Graph-based semi-supervised learning： a comprehensive review［J］. IEEE Transactions on Neural Networks and Learning Systems， 2023， 34（11）： 8174-8194.
[42]	ZANG H， WAN X. A semi-supervised approach for low-resourced text generation［EB/OL］. ［2025-04-23］..
[43]	MENG Y， SHEN J， ZHANG C， et al. Weakly-supervised neural text classification［C］// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York： ACM， 2018： 983-992.
[44]	LIU Y， JIN M， PAN S， et al. Graph self-supervised learning： a survey［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（6）： 5879-5900.
[45]	BOND-TAYLOR S， LEACH A， LONG Y， et al. Deep generative modelling： a comparative review of VAEs， GANs， normalizing flows， energy-based and autoregressive models［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2022， 44（11）： 7327-7347.
[46]	LI C， ZHU J， ZHANG B. Max-margin deep generative models for （semi-）supervised learning［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2018， 40（11）： 2762-2775.
[47]	CAPROLU M， SADIGHIAN A， DI PIETRO R. Characterizing the 2022 Russo-Ukrainian conflict through the lenses of aspect-based sentiment analysis： dataset， methodology， and key findings［C］// Proceedings of the 32nd International Conference on Computer Communications and Networks. Piscataway： IEEE， 2023： 1-10.
[48]	GOLDBERG Y， LEVY O. word2vec Explained： deriving Mikolovet al.’s negative-sampling word-embedding method［EB/OL］. ［2025-04-23］..
[49]	RODRÍGUEZ P， BAUTISTA M A， GONZÀLEZ J， et al. Beyond one-hot encoding： lower dimensional target embedding［J］. Image and Vision Computing， 2018， 75： 21-31.
[50]	BARABÁSI A L， ALBERT R. Emergence of scaling in random networks［J］. Science， 1999， 286（5439）： 509-512.
[51]	CRESCI S， DI PIETRO R， PETROCCHI M， et al. The paradigm-shift of social spambots： evidence， theories， and tools for the arms race［C］// Proceedings of the 26th International Conference on World Wide Web Companion. Republic and Canton of Geneva： International World Wide Web Conferences Steering Committee， 2017： 963-972.
[52]	MARWICK A E， BOYD D. I tweet honestly， I tweet passionately： Twitter users， context collapse， and the imagined audience［J］. New Media and Society， 2011， 13（1）： 114-133.
[53]	CRESCI S， DI PIETRO R， PETROCCHI M， et al. Fame for sale： efficient detection of fake Twitter followers［J］. Decision Support Systems， 2015， 80： 56-71.
[54]	FENG S， WAN H， WANG 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.
[55]	CORTES C， VAPNIK V. Support-vector networks［J］. Machine Learning， 1995， 20（3）： 273-297.
[56]	BREIMAN L. Random forests［J］. Machine Learning， 2001， 45（1）： 5-32.
[57]	CRESCI S， DI PIETRO R， PETROCCHI M， et al. DNA-inspired online behavioral modeling and its application to spambot detection［J］. IEEE Intelligent Systems， 2016， 31（5）： 58-64.
[58]	FENG S， WAN H， WANG N， et al. SATAR： a self-supervised approach to Twitter account representation learning and its application in bot detection［C］// Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York： ACM， 2021： 3808-3817.
[59]	LIU Y， OTT M， GOYAL N， et al. RoBERTa： a robustly optimized BERT pretraining approach［EB/OL］. ［2025-04-23］..
[60]	FENG S， WAN H， WANG 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.
[61]	FENG S， TAN Z， LI R， et al. Heterogeneity-aware Twitter bot detection with relational graph transformers［C］// Proceedings of the 36th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2022： 3977-3985.
[62]	FENG S， WAN H， WANG N， et al. What does the bot say？ opportunities and risks of large language models in social media bot detection［C］// Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg： ACL， 2024： 3580-3601.

数据集	用户总数	机器人用户数	人类用户数
Cresci-15^［53］	5 301	3 351	1 950
Cresci-17^［51］	9 813	7 049	2 764
TwiBot-20^［54］	11 826	6 589	5 237

数据集	用户总数	机器人用户数	人类用户数
Cresci-15^［53］	5 301	3 351	1 950
Cresci-17^［51］	9 813	7 049	2 764
TwiBot-20^［54］	11 826	6 589	5 237

方法	框架	描述
基于特征工程的传统机器学习方法	SVM^［55］	最早应用于僵尸检测的分类器之一，利用用户属性和行为统计数据构建线性或非线性决策边界
基于特征工程的传统机器学习方法	RF^［56］	一种结合多个决策树的集合模型，能够处理离散和连续混合特征，用于社交数据中的异常检测
端到端传统深度学习方法	Cresci等^［57］	将用户行为序列编码成字符串，并通过识别最长公共子串检测机器人，从而有效捕捉账户组内的行为相似性
	SATAR^［58］	通过监督微调整合语义内容、用户属性和社交关系，捕捉全面的行为模式，用于僵尸检测
	RoBERTa^［59］	利用预训练的RoBERTa语言模型对推文文本进行编码，然后利用分类头进行僵尸识别
图分析深度学习和社区发现方法	SGBot^［8］	将文本和属性特征与图卷积网络相结合，为用户互动建模，强调社会结构在行为表征中的贡献
	BotRGCN^［60］	采用关系图卷积网络（R-GCN）将各种类型的社会关系建模为多关系图，用于节点级表示学习
	RGT^［61］	构建异构信息网络（HINs），并采用多头关注和语义聚合的关系图转换器捕捉复杂的关系动态
基于LLM的方法	Feng等^［62］	提出了一种专家混合框架，利用LLMs通过上下文学习和指令调整处理元数据、文本内容和社会结构，并通过多数投票进行最终预测汇总
本文方法	W2A-BotNet	一个包含多模态数据表示学习、基于小波的频域增强、协作特征融合和自监督预训练机制的统一检测框架

方法	框架	描述
基于特征工程的传统机器学习方法	SVM^［55］	最早应用于僵尸检测的分类器之一，利用用户属性和行为统计数据构建线性或非线性决策边界
基于特征工程的传统机器学习方法	RF^［56］	一种结合多个决策树的集合模型，能够处理离散和连续混合特征，用于社交数据中的异常检测
端到端传统深度学习方法	Cresci等^［57］	将用户行为序列编码成字符串，并通过识别最长公共子串检测机器人，从而有效捕捉账户组内的行为相似性
	SATAR^［58］	通过监督微调整合语义内容、用户属性和社交关系，捕捉全面的行为模式，用于僵尸检测
	RoBERTa^［59］	利用预训练的RoBERTa语言模型对推文文本进行编码，然后利用分类头进行僵尸识别
图分析深度学习和社区发现方法	SGBot^［8］	将文本和属性特征与图卷积网络相结合，为用户互动建模，强调社会结构在行为表征中的贡献
	BotRGCN^［60］	采用关系图卷积网络（R-GCN）将各种类型的社会关系建模为多关系图，用于节点级表示学习
	RGT^［61］	构建异构信息网络（HINs），并采用多头关注和语义聚合的关系图转换器捕捉复杂的关系动态
基于LLM的方法	Feng等^［62］	提出了一种专家混合框架，利用LLMs通过上下文学习和指令调整处理元数据、文本内容和社会结构，并通过多数投票进行最终预测汇总
本文方法	W2A-BotNet	一个包含多模态数据表示学习、基于小波的频域增强、协作特征融合和自监督预训练机制的统一检测框架

检测方法	Cresci-15			Cresci-17			TwiBot-20
检测方法	ACC	F1-score	MCC	ACC	F1-score	MCC	ACC	F1-score	MCC
SVM^［55］	0.631 8	0.884 3	0.802 4	0.803 1	0.792 8	0.733 2	0.462 3	0.593 1	0.523 4
RF^［56］	0.631 0	0.774 3	0.534 2	0.758 4	0.862 6	0.643 1	0.534 1	0.538 1	0.441 2
Cresci等^［57］方法	0.835 3	0.884 3	0.802 4	0.803 1	0.792 8	0.733 2	0.477 6	0.136 9	0.054 5
SATAR^［58］	0.938 3	0.953 3	0.870 2	0.856 4	0.858 0	0.114 7	0.832 4	0.803 1	0.682 2
RoBERTa^［59］	0.949 5	0.927 6	0.892 4	0.835 3	0.659 0	0.550 4	0.750 6	0.736 4	0.501 0
SGBot^［8］	0.760 7	0.767 2	0.610 6	0.917 0	0.942 9	0.822 0	0.814 9	0.847 2	0.641 7
BotRGCN^［60］	0.953 3	0.963 9	0.899 9	0.803 1	0.792 8	0.733 2	0.813 2	0.810 4	0.623 1
RGT^［61］	0.942 6	0.951 1	0.880 2	0.923 0	0.935 0	0.815 2	0.810 6	0.828 0	0.618 0
Feng等^［62］方法	0.987 0	0.973 3	0.874 2	0.943 1	0.910 0	0.876 2	0.831 0	0.823 3	0.654 3
W2A‑BotNet	0.990 5	0.990 4	0.979 8	0.991 7	0.966 3	0.953 8	0.854 5	0.883 1	0.708 2

Social bot detection framework fusing multi-scale wavelet enhancement and self-supervised learning

融合多尺度小波增强与自监督学习的社交机器人检测框架

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 62

Related Articles 15

Recommended Articles

Metrics

消融特征	ACC	F1-score	MCC
Neighbor	0.779 4	0.851 0	0.542 5
Property	0.832 9	0.853 3	0.678 2
Tweet	0.802 4	0.838 9	0.635 7

消融模块	ACC	F1-score	MCC
-SS	0.659 6	0.736 2	0.317 2
-A	0.829 6	0.852 8	0.653 9
-W	0.803 0	0.842 9	0.614 6
-C	0.838 5	0.862 5	0.673 4
-SS & -W	0.645 5	0.697 0	0.306 5
-SS & -C	0.649 9	0.713 3	0.295 4
-SS & -A	0.603 2	0.702 4	0.301 9
-W & -C	0.764 2	0.809 1	0.602 9
-W & -A	0.759 2	0.799 2	0.601 4
-C & -A	0.805 5	0.843 2	0.609 1

[1]	Haoran YUAN, Huan LIU, Pengfei JIAO, Zhidong ZHAO, Xianfei ZHANG, Zunliang LIU. Masked autoencoder enhanced dynamic heterogeneous graph representation learning model [J]. Journal of Computer Applications, 2026, 46(6): 1728-1737.
[2]	Kun FU, Haoyu WEI, Weijing LIU, Xing DANG, Zezheng LIU, Jianwei LI. Graph neural network framework for topology semantic dual-domain collaboration [J]. Journal of Computer Applications, 2026, 46(5): 1378-1387.
[3]	Xiaobo QI, Jing ZHANG, Ying SHI, Hui QI, Hangyuan DU. Multiple active learning method based on concept drift detection [J]. Journal of Computer Applications, 2026, 46(5): 1388-1396.
[4]	Fengwei CHENG, Bingqi ZHANG, Guohua XU, Wenjian WANG. Competitive loss-driven generative imbalanced node classification [J]. Journal of Computer Applications, 2026, 46(5): 1475-1481.
[5]	Chi ZHANG, Xianjing MENG, Changhao DOU, Qian WANG, Leilei GENG, Xiaoming XI. MD-FVR： cascaded finger vein recognition network based on multi-domain feature fusion [J]. Journal of Computer Applications, 2026, 46(5): 1658-1666.
[6]	Xumeng DOU, Bin XIE, Zhaohui ZHANG, Zhengang ZHAO, Hanyu DUAN, Aolei GUO. Drug-target interaction prediction based on structure-network collaborative features and grid-attention enhanced Kolmogorov-Arnold network [J]. Journal of Computer Applications, 2026, 46(4): 1344-1353.
[7]	Shengwei XU, Jianbo WANG, Jijie HAN, Yijie BAI. Face forgery detection method based on tri-branch feature extraction [J]. Journal of Computer Applications, 2026, 46(4): 1292-1299.
[8]	Zhige HE, Chang LIU, Junrui WU, Haoran LUO, Shuisong HU, Wenyong WANG. Review of DDoS attack defense technology [J]. Journal of Computer Applications, 2026, 46(4): 1139-1157.
[9]	Rilong WANG, Zhenping LI, Xiaosong LI, Qiang GAO, Ya HE, Yong ZHONG, Yingxiao ZHAO. Multi-Agent collaborative knowledge reasoning framework [J]. Journal of Computer Applications, 2026, 46(3): 708-714.
[10]	Yongwei JIANG, Xiaoqing CHEN, Linjie FU. Elastic medical image registration model with high-frequency preservation based on spectrum decomposition [J]. Journal of Computer Applications, 2026, 46(3): 924-932.
[11]	Enkang XI, Jing FAN, Yadong JIN, Hua DONG, Hao YU, Yihang SUN. Review of threats faced by federated learning in privacy and security field [J]. Journal of Computer Applications, 2026, 46(3): 798-808.
[12]	Huihui CHEN, Hongtao SUN, Boliang GUAN, Zhongqing HENG. Chinese character image retrieval algorithm in ancient books based on NetVLAD feature encoding [J]. Journal of Computer Applications, 2026, 46(3): 750-757.
[13]	Yan HU, Peng LI, Shuyan CHENG. Adversarial purification method based on directly guided diffusion model [J]. Journal of Computer Applications, 2026, 46(3): 821-829.
[14]	Kaiguang MA, Xuebin CHEN, Yinlong JIAN, Liu WANG, Yuan GAO. Network intrusion detection based on hybrid sequence model and federated class balance algorithm [J]. Journal of Computer Applications, 2026, 46(3): 857-866.
[15]	Junrui WU, Jiangchuan YANG, Haisheng YU, Sai ZOU, Wenyong WANG. Performance evaluation method for deterministic networks based on complex-enhanced attention graph neural network [J]. Journal of Computer Applications, 2026, 46(2): 505-517.