Masked autoencoder enhanced dynamic heterogeneous graph representation learning model

doi:10.11772/j.issn.1001-9081.2025060754

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (6): 1728-1737.DOI: 10.11772/j.issn.1001-9081.2025060754

• Artificial intelligence • Previous Articles

Masked autoencoder enhanced dynamic heterogeneous graph representation learning model

Haoran YUAN¹, Huan LIU¹, Pengfei JIAO¹^,², Zhidong ZHAO¹(), Xianfei ZHANG³, Zunliang LIU⁴

^1.School of Cyberspace Security，Hangzhou Dianzi University，Hangzhou Zhejiang 310018，China
^2.Zhejiang Provincial Engineering Research Center for Data Security Governance （Hangzhou Dianzi University），Hangzhou Zhejiang 310018，China
^3.School of Electronics and Information，Hangzhou Dianzi University，Hangzhou Zhejiang 310018，China
^4.Hangzhou Meichuang Technology Company Limited，Hangzhou Zhejiang 310015，China

Received:2025-07-09 Revised:2026-01-12 Accepted:2026-01-26 Online:2026-01-29 Published:2026-06-10
Contact: Zhidong ZHAO
About author:YUAN Haoran， born in 2000， M. S. His research interests include graph neural network， data mining.
LIU Huan， born in 1999， Ph. D. candidate. His research interests include complex network analysis， graph neural network， data mining.
JIAO Pengfei， born in 1990， Ph. D.， professor. His research interests include complex network analysis and its application.
ZHANG Xianfei， born in 1980， M. S.， associate professor. His research interests include autonomous unmanned system， medical signal analysis.
LIU Zunliang， born in 1970， senior engineer. His research interests include data management， information security.
First author contact:ZHAO Zhidong， born in 1976， Ph. D.， professor. His research interests include explainable artificial intelligence， signal system.
Supported by:
General Program of National Natural Science Foundation of China(62372146);“Pioneer” and “Leading Goose” Research and Development Program of Zhejiang Province(2024C01023)

掩码自编码器增强的动态异质图表示学习模型

袁浩然¹, 刘欢¹, 焦鹏飞¹^,², 赵治栋¹(), 张显飞³, 柳遵梁⁴

^1.杭州电子科技大学网络空间安全学院，杭州 310018
^2.数据安全治理浙江省工程研究中心（杭州电子科技大学），杭州 310018
^3.杭州电子科技大学电子信息学院，杭州 310018
^4.杭州美创科技股份有限公司，杭州 310015

通讯作者: 赵治栋
作者简介:袁浩然（2000—），男，江苏靖江人，硕士，主要研究方向：图神经网络、数据挖掘
刘欢（1999—），男，河南周口人，博士研究生，CCF会员，主要研究方向：复杂网络分析、图神经网络、数据挖掘
焦鹏飞（1990—），男，河南洛阳人，教授，博士，CCF会员，主要研究方向：复杂网络分析及其应用
张显飞（1980—），男，安徽宿松人，副教授，硕士，主要研究方向：自主无人系统、医疗信号分析
柳遵梁（1970—），男，浙江宁波人，高级工程师，主要研究方向：数据管理、信息安全。
第一联系人：共同第一作者
赵治栋（1976—），男，山东泰安人，教授，博士，主要研究方向：可解释人工智能、信号系统
基金资助:
国家自然科学基金面上项目(62372146);浙江省“尖兵”“领雁”研发攻关计划项目(2024C01023);浙江省“尖兵”“领雁”研发攻关计划项目(2024C01102);浙江省“尖兵”“领雁”研发攻关计划项目(2025C01023)

Abstract

Abstract:

Real-world networks are often composed of multiple types of entities and interaction relationships， with topological structure and attributes evolving with time continuously. The heterogeneity and dynamics inherent in such networks can be fully described by Dynamic Heterogeneous Graph （DHG）. To solve the problems of coarse spatio-temporal information fusion and heavy reliance of the supervised learning paradigm on manual labels in the existing DHG representation learning models， a Masked AutoEncoder （MAE） enhanced DHG representation learning model was proposed. Firstly， heterogeneous spatial information was fused through a multi-level attention structure， and temporal information was fused across snapshots. Then， representation information of nodes was enriched by leveraging the reconstruction loss of the masked autoencoder. Experimental results show that improvements of at least 1.26 to 3.99 percentage points in Area Under the receiver operating Characteristic curve （AUC） are achieved by the proposed model on link prediction tasks compared to baseline models on multiple real-world datasets. It can be seen that the proposed model provides an effective self-supervised framework for DHG representation learning， facilitating more precise capture of heterogeneous information and dynamic evolution laws in real networks.

Key words: representation learning, Dynamic Heterogeneous Graph (DHG), Masked AutoEncoder (MAE), self-supervised learning, link prediction

摘要：

现实世界网络通常由多类型实体和交互关系构成，且拓扑结构及属性随时间不断演化。这些网络所蕴含的异质性和动态性可以通过动态异质图（DHG）数据完整描述。为了解决现有DHG表示学习模型存在的时空信息融合较粗糙，及它们的监督学习范式强依赖于人工标签的问题，提出掩码自编码器（MAE）增强的DHG表示学习模型。首先，通过多层次注意力结构融合异质空间信息，并进行跨快照的时间信息聚合；其次，利用掩码自编码器的重建损失丰富节点的表示信息。实验结果表明，所提模型在多个真实世界数据集上的链路预测任务中相较于基线模型有至少1.26~3.99个百分点的受试者工作特征曲线下面积（AUC）提升。可见，所提模型为DHG表示学习提供了一个有效的自监督框架，有助于更精确地捕捉真实网络中的异质信息与动态演化规律。

关键词: 表征学习, 动态异质图, 掩码自编码器, 自监督学习, 链路预测

CLC Number:

TP391.1

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.

袁浩然, 刘欢, 焦鹏飞, 赵治栋, 张显飞, 柳遵梁. 掩码自编码器增强的动态异质图表示学习模型[J]. 《计算机应用》唯一官方网站, 2026, 46(6): 1728-1737.

Figures/Tables 8

Tab. 1 Mathematical symbols and their meanings

符号	含义
$G, G ̂$	动态异质图及掩码后动态异质图
$G t, G ̂ t$	第 $t$ 时间步异质图及掩码异质图
$A t, A [M A S K] t$	第 $t$ 时间步异质图邻接矩阵及掩码矩阵
$X, X ̂$	节点属性矩阵及掩码后属性矩阵
$H, H ̂$	原始图与掩码图隐藏层节点嵌入矩阵
$Z$	模型最终输出节点嵌入矩阵
$W, b$	可学习变换权重矩阵及偏置向量
$Q, K, V$	注意力机制中的查询、键和值矩阵
$M$	时序注意力的因果掩码矩阵
$h i, z i$	节点隐藏层嵌入向量及输出表征向量
$x i, x M A S K$	节点原始属性向量及掩码标记向量
$h R E M A S K$	特征重构前的再掩码标记向量
$a$	注意力机制中注意力分数变换向量
$P E (t)$	第 $t$ 时间步的时序位置编码向量

Tab. 1 Mathematical symbols and their meanings

符号	含义
$G, G ̂$	动态异质图及掩码后动态异质图
$G t, G ̂ t$	第 $t$ 时间步异质图及掩码异质图
$A t, A [M A S K] t$	第 $t$ 时间步异质图邻接矩阵及掩码矩阵
$X, X ̂$	节点属性矩阵及掩码后属性矩阵
$H, H ̂$	原始图与掩码图隐藏层节点嵌入矩阵
$Z$	模型最终输出节点嵌入矩阵
$W, b$	可学习变换权重矩阵及偏置向量
$Q, K, V$	注意力机制中的查询、键和值矩阵
$M$	时序注意力的因果掩码矩阵
$h i, z i$	节点隐藏层嵌入向量及输出表征向量
$x i, x M A S K$	节点原始属性向量及掩码标记向量
$h R E M A S K$	特征重构前的再掩码标记向量
$a$	注意力机制中注意力分数变换向量
$P E (t)$	第 $t$ 时间步的时序位置编码向量

Fig. 1 Framework of MAE enhanced dynamic heterogeneous graph representation model

Tab. 2 Experimental DHG dataset statistics

数据集	节点（节点数）	边类型（边数）	快照数
OGBN	作者（17 764），	作者-论文（2 061 677），	10
	论文（282 039），	论文-论文（2 377 564），
	领域（34 601），	论文-领域（289 376），
	机构（2 276）	作者-机构（40 307）
AMiner	作者（8 882），	作者-论文（7 538），	12
	论文（7 289），	作者-会议（7 538），
	会议（1 970）	论文-会议（1 634）
DBLP	作者（8 470），	作者-论文（8 056），	12
	论文（9 025），	作者-会议（8 056），
	会议（1 074）	论文-会议（1 903）
Yelp	用户（1 452），	商家-评分（1 080），	9
	商家（771），	商家-用户（1 080），
	评分（5）	用户-评分（1 080）

Tab. 3 Link prediction experimental results （presented in mean ± standard deviation format）

模型	OGBN		AMiner		DBLP		Yelp
模型	AUC	AP	AUC	AP	AUC	AP	AUC	AP
GAT	80.23±2.07	77.58±1.74	62.25±0.73	63.91±0.54	59.65±0.88	58.78±1.04	57.73±2.46	59.21±1.17
DGI	64.04±2.38	72.97±1.67	59.26±5.05	62.65±4.78	55.45±1.59	61.45±3.42	55.21±2.44	57.34±3.41
HGT	85.30±1.20	82.68±1.20	64.48±5.34	65.07±4.43	54.89±5.11	55.31±5.08	60.15±5.27	60.42±4.28
SimpleHGN	88.73±1.74	86.14±1.71	65.07±3.70	64.36±2.81	62.26±4.19	57.86±3.74	63.65±2.85	57.41±3.70
HDE	83.76±0.67	81.24±1.31	63.28±1.54	64.95±2.12	59.16±5.11	59.43±5.08	59.37±3.46	56.60±3.15
R-GCN	80.34±0.22	78.11±0.16	58.12±3.46	57.20±3.23	55.61±2.90	53.97±3.08	62.21±1.10	58.18±1.64
EvolveGCN	84.37±1.04	81.86±0.98	61.74±2.08	64.83±1.53	53.67±2.99	51.93±3.42	57.24±3.12	53.74±2.47
DySAT	86.36±0.24	83.83±0.29	62.31±3.57	64.54±3.22	54.86±2.58	53.39±2.43	59.17±4.24	60.24±4.31
HTGNN	91.01±0.77	89.18±0.12	66.30±2.60	65.85±2.35	65.82±1.54	66.53±1.73	65.64±3.94	62.37±4.77
本文模型	92.27±0.23	90.84±0.19	69.71±1.26	69.43±1.43	68.12±3.06	68.73±2.80	69.63±1.70	67.31±1.40

Fig. 2 Ablation experimental results of proposed model on four datasets

Fig. 3 Four super parameter sensitivity analysis on four datasets

Fig. 4 Sensitivity analysis of replacement and retention rates on four datasets

Fig. 5 Sensitivity analysis of fixed and dynamic masking rates on four datasets

References 51

[1]	CUI P， WANG X， PEI J， et al. A survey on network embedding［J］. IEEE Transactions on Knowledge and Data Engineering， 2019， 31（5）： 833-852.
[2]	HAMILTON W L， YING R， LESKOVEC J. Representation learning on graphs： methods and applications［EB/OL］. ［2025-04-19］..
[3]	YING R， HE R， CHEN K， et al. Graph convolutional neural networks for web-scale recommender systems［C］// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2018： 974-983.
[4]	PANG Y， WU L， SHEN Q， et al. Heterogeneous global graph neural networks for personalized session-based recommendation［C］// Proceedings of the 15th ACM International Conference on Web Search and Data Mining. New York： ACM， 2022： 775-783.
[5]	ZHANG Z， CHEN L， ZHONG F， et al. Graph neural network approaches for drug-target interactions［J］. Current Opinion in Structural Biology， 2022， 73： No.102327.
[6]	LIU T， LI P， GU Y. Glint： decentralized federated graph learning with traffic throttling and flow scheduling［C］// Proceedings of the 2021 IEEE/ACM 29th International Symposium on Quality of Service. Piscataway： IEEE， 2021： 1-10.
[7]	JIANG B， ZHANG Z， LIN D， et al. Semi-supervised learning with graph learning-convolutional networks［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 11305-11312.
[8]	VELIČKOVIĆ P， CUCURULL G， CASANOVA A， et al. Graph attention networks［EB/OL］. ［2025-04-19］..
[9]	DONG Y， CHAWLA N V， SWAMI A. metapath2vec： scalable representation learning for heterogeneous networks［C］// Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2017： 135-144.
[10]	TRIVEDI R， FARAJTABAR M， BISWAL P， et al. DyRep： learning representations over dynamic graphs［EB/OL］. ［2025-04-19］..
[11]	BARROS C D T， MENDONÇA M R F， VIEIRA A B， et al. A survey on embedding dynamic graphs［J］. ACM Computing Surveys， 2023， 55（1）： No.10.
[12]	LI T， WANG W， JIAO P， et al. Exploring temporal community structure via network embedding［J］. IEEE Transactions on Cybernetics， 2023， 53（11）： 7021-7033.
[13]	LIU H， JIAO P， GUO X， et al. HGN2T： a simple but plug-and-play framework extending HGNNs on heterogeneous temporal graphs［J］. IEEE Transactions on Big Data， 2024， 10（5）： 620-632.
[14]	LUO W， ZHANG H， YANG X， et al. Dynamic heterogeneous graph neural network for real-time event prediction［C］// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2020： 3213-3223.
[15]	XIE Y， OU Z， CHEN L， et al. Learning and updating node embedding on dynamic heterogeneous information network［C］// Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York： ACM， 2021： 184-192.
[16]	FAN Y， JU M， ZHANG C， et al. Heterogeneous temporal graph neural network［C］// Proceedings of the 2022 SIAM International Conference on Data Mining. Philadelphia， PA： SIAM， 2022： 657-665.
[17]	WANG X， LU Y， SHI C， et al. Dynamic heterogeneous information network embedding with meta-path based proximity［J］. IEEE Transactions on Knowledge and Data Engineering， 2022， 34（3）： 1117-1132.
[18]	WANG X， LIU N， HAN H， et al. Self-supervised heterogeneous graph neural network with co-contrastive learning［C］// Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2021： 1726-1736.
[19]	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.
[20]	焦鹏飞，刘欢，吕乐，等. 基于对比学习的全局增强动态异质图神经网络［J］. 计算机研究与发展， 2023， 60（8）： 1808-1821.
	JIAO P F， LIU H， LYU L， et al. Globally enhanced heterogeneous temporal graph neural networks based on contrastive learning［J］. Journal of Computer Research and Development， 2023， 60（8）： 1808-1821.
[21]	LIU X， ZHANG F， HOU Z， et al. Self-supervised learning： generative or contrastive［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（1）： 857-876.
[22]	HOU Z， LIU X， CEN Y， et al. GraphMAE： self-supervised masked graph autoencoders［C］// Proceedings of the 28th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2022： 594-604.
[23]	YOU Y， CHEN T， SHEN Y， et al. Graph contrastive learning automated［C］// Proceedings of the 38th International Conference on Machine Learning. New York： JMLR.org， 2021： 12121-12132.
[24]	HE K， CHEN X， XIE S， et al. Masked autoencoders are scalable vision learners［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 15979-15988.
[25]	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.
[26]	杭州电子科技大学，杭州美创科技股份有限公司. 基于掩码自编码器的动态异质图表示学习方法：202510252018.9［P］. 2025-06-20.
	Hangzhou Dianzi University， Hangzhou Meichuang Technology Company Limited. Dynamic heterogeneous graph representation learning method based on masked autoencoder： 202510252018.9［P］. 2025-06-20.
[27]	袁浩然. 基于Transformer的动态异质图表示学习［D］. 杭州：杭州电子科技大学， 2025： 22-39.
	YUAN H R. Transformer-based dynamic heterogeneous graph representation learning［D］. Hangzhou： Hangzhou Dianzi University， 2025： 22-39.
[28]	PEROZZI B， AL-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.
[29]	GROVER A， LESKOVEC 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.
[30]	HAMILTON W L， YING R， LESKOVEC J. Inductive representation learning on large graphs［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 1025-1035.
[31]	SUN Y， HAN J. Mining heterogeneous information networks： a structural analysis approach［J］. ACM SIGKDD Explorations Newsletter， 2012， 14（2）： 20-28.
[32]	GUO X， JIAO P， ZHANG W， et al. Representation learning on heterostructures via heterogeneous anonymous walks［J］. IEEE Transactions on Neural Networks and Learning Systems， 2024， 35（7）： 9538-9552.
[33]	SCHLICHTKRULL M， KIPF T N， BLOEM P， et al. Modeling relational data with graph convolutional networks ［C］// Proceedings of the 2018 European Semantic Web Conference， LNCS 10843. Cham： Springer， 2018： 593-607.
[34]	WANG X， JI H， SHI C， et al. Heterogeneous graph attention network［C］// Proceedings of the 2019 World Wide Web Conference. New York： ACM， 2019： 2022-2032.
[35]	HU Z， DONG Y， WANG K， et al. Heterogeneous graph Transformer［C］// Proceedings of the World Wide Web Conference 2020. New York： ACM， 2020： 2704-2710.
[36]	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 6000-6010.
[37]	FU X， ZHANG J， MENG Z， et al. MAGNN： metapath aggregated graph neural network for heterogeneous graph embedding［C］// Proceedings of the Web Conference 2020. New York： ACM， 2020： 2331-2341.
[38]	HONG H， GUO H， LIN Y， et al. An attention-based graph neural network for heterogeneous structural learning［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2020： 4132-4139.
[39]	DU L， WANG Y， SONG G， et al. Dynamic network embedding： an extended approach for skip-gram based network embedding［C］// Proceedings of the 27th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2018： 2086-2092.
[40]	ZHOU L， YANG Y， REN X， et al. Dynamic network embedding by modeling triadic closure process［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2018： 571-578.
[41]	GOYAL P， KAMRA N， HE X， et al. DynGEM： deep embedding method for dynamic graphs ［EB/OL］. ［2025-04-19］..
[42]	PAREJA A， DOMENICONI G， CHEN J， et al. EvolveGCN： evolving graph convolutional networks for dynamic graphs［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2020： 5363-5370.
[43]	SANKAR A， WU Y， GOU L， et al. DySAT： deep neural representation learning on dynamic graphs via self-attention networks［C］// Proceedings of the 13th International Conference on Web Search and Data Mining. New York： ACM， 2020： 519-527.
[44]	XUE H， YANG L， JIANG W， et al. Modeling dynamic heterogeneous network for link prediction using hierarchical attention with temporal RNN［C］// Proceedings of the 2020 European Conference on Machine Learning and Knowledge Discovery in Databases， LNCS 12457. Cham： Springer， 2021： 282-298.
[45]	YOU J， YING R， REN X， et al. GraphRNN： generating realistic graphs with deep auto-regressive models ［C］// Proceedings of the 35th International Conference on Machine Learning. New York： JMLR.org， 2018： 5708-5717.
[46]	KIPF T N， WELLING M. Variational graph auto-encoders［EB/OL］. ［2025-04-19］..
[47]	REN Y， LIU B， HUANG C， et al. Heterogeneous deep graph Infomax［EB/OL］. ［2025-04-19］..
[48]	VELIČKOVIĆ P， FEDUS W， HAMILTON W L， et al. Deep graph infomax［EB/OL］. ［2025-04-19］..
[49]	TIAN Y， DONG K， ZHANG C， et al. Heterogeneous graph masked autoencoders［C］// Proceedings of the 37th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2023： 9997-10005.
[50]	YANG X， YAN M， PAN S， et al. Simple and efficient heterogeneous graph neural network ［C］// Proceedings of the 37th AAAI Conference on Artificial Intelligence. Palo Alto：AAAI Press， 2023： 10816-10824.
[51]	JI H， YANG C， SHI C， et al. Heterogeneous Graph Neural Network with Distance Encoding［C］// Proceedings of the 2021 IEEE International Conference on Data Mining. Piscataway：IEEE， 2021： 1138-1143.

Masked autoencoder enhanced dynamic heterogeneous graph representation learning model

掩码自编码器增强的动态异质图表示学习模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 51

Related Articles 15

Recommended Articles

Metrics

[1]	Jing ZHANG, Songhua LIU, Yuanqian ZHU. Time series representation method based on spectral sensing and hierarchical convolution [J]. Journal of Computer Applications, 2026, 46(4): 1124-1130.
[2]	Haoyang ZHANG, Liping ZHANG, Sheng YAN, Na LI, Xuefei ZHANG. Review of large language model methods for knowledge graph completion [J]. Journal of Computer Applications, 2026, 46(3): 683-695.
[3]	Qiao YU, Zirui HUANG, Shengyi CHENG, Yi ZHU, Shutao ZHANG. Software vulnerability detection method based on edge weight [J]. Journal of Computer Applications, 2026, 46(2): 518-527.
[4]	Ziyang CHENG, Ruizhang HUANG, Jingjing XUE. Deep evolutionary topic clustering model [J]. Journal of Computer Applications, 2026, 46(1): 85-94.
[5]	Wen LI, Kairong LI, Kai YANG. Subgraph-aware contrastive learning with data augmentation [J]. Journal of Computer Applications, 2026, 46(1): 1-9.
[6]	Chao LIU, Yanhua YU. Knowledge-aware recommendation model combining denoising strategy and multi-view contrastive learning [J]. Journal of Computer Applications, 2025, 45(9): 2827-2837.
[7]	Penghuan QU, Wei WEI, Jing YAN, Feng WANG. Dual imputation based incomplete multi-view metric learning [J]. Journal of Computer Applications, 2025, 45(9): 2755-2763.
[8]	Yi WANG, Yinglong MA. Multi-task social item recommendation method based on dynamic adaptive generation of item graph [J]. Journal of Computer Applications, 2025, 45(8): 2592-2599.
[9]	Yifeng PENG, Yan ZHU. Combining preprocessing methods and adversarial learning for fair link prediction [J]. Journal of Computer Applications, 2025, 45(8): 2566-2571.
[10]	Zonghang WU, Dong ZHANG, Guanyu LI. Multimodal fusion recommendation algorithm based on joint self-supervised learning [J]. Journal of Computer Applications, 2025, 45(6): 1858-1868.
[11]	Haijie WANG, Guangxin ZHANG, Hai SHI, Shu CHEN. Document-level relation extraction based on entity representation enhancement [J]. Journal of Computer Applications, 2025, 45(6): 1809-1816.
[12]	Yufei LONG, Yuchen MOU, Ye LIU. Multi-source data representation learning model based on tensorized graph convolutional network and contrastive learning [J]. Journal of Computer Applications, 2025, 45(5): 1372-1378.
[13]	Junyi ZHU, Leilei CHANG, Xiaobin XU, Zhiyong HAO, Haiyue YU, Jiang JIANG. Self-supervised learning method using minimal prior knowledge [J]. Journal of Computer Applications, 2025, 45(4): 1035-1041.
[14]	Guangju YANG, Tianjian LUO, Kaijun WANG, Siqi YANG. Multi-branch multi-view based contextual contrastive representation learning method for time series [J]. Journal of Computer Applications, 2025, 45(4): 1042-1052.
[15]	Sheping ZHAI, Qing YANG, Yan HUANG, Rui YANG. Knowledge graph completion using hierarchical attention fusing directed relationships and relational paths [J]. Journal of Computer Applications, 2025, 45(4): 1148-1156.