Deep evolutionary topic clustering model

doi:10.11772/j.issn.1001-9081.2025010126

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (1): 85-94.DOI: 10.11772/j.issn.1001-9081.2025010126

• Data science and technology • Previous Articles Next Articles

Deep evolutionary topic clustering model

Ziyang CHENG¹^,², Ruizhang HUANG¹^,²(), Jingjing XUE¹^,²

^1.State Key Laboratory of Public Big Data （Guizhou University），Guiyang Guizhou 550025，China
^2.College of Computer Science and Technology，Guizhou University，Guiyang Guizhou 550025，China

Received:2025-02-10 Revised:2025-04-29 Accepted:2025-04-29 Online:2026-01-10 Published:2026-01-10
Contact: Ruizhang HUANG
About author:CHENG Ziyang， born in 2000， M. S. candidate. His research interests include topic information mining， evolutionary clustering.
XUE Jingjing， born in 1995， Ph. D. candidate. Her research interests include deep text clustering.
Supported by:
National Natural Science Foundation of China(62066007);Guizhou Provincial Science and Technology Support Program （Qiankehe Support ［2023］ General 300;Qiankehe Support ［2023］ General 448

深度演化主题聚类模型

程梓洋¹^,², 黄瑞章¹^,²(), 薛菁菁¹^,²

^1.公共大数据国家重点实验室（贵州大学），贵阳 550025
^2.贵州大学计算机科学与技术学院，贵阳 550025

通讯作者: 黄瑞章
作者简介:程梓洋（2000—），男，贵州贵阳人，硕士研究生，主要研究方向：主题信息挖掘、演化聚类
薛菁菁（1995—），女，山东日照人，博士研究生，CCF会员，主要研究方向：深度文本聚类。
基金资助:
国家自然科学基金资助项目(62066007);贵州省科技支撑计划项目（黔科合支撑［2023］一般300;黔科合支撑［2023］一般448

Abstract

Abstract:

To address challenges related to topic ambiguity and inaccurate alignment problems in the existing deep document clustering methods when processing dynamic textual data with topics varying with time， a Deep Evolutionary Topic Clustering Model （DETCM） was proposed. In DETCM， information of topics varying with time was captured in dynamic text， and historical topic information was integrated with document features of the current time slice， thereby discovering event topic trajectories and generating dynamic document topic representations. In specific， to solve topic ambiguity problem of topics varying with time， a topic fusion learning module based on a hybrid encoder was designed， in which topic information from preceding time slices was utilized to enhance topic discrimination and feature extraction of the current time slice. Furthermore， a topic inheritance module across different time slices was designed to achieve topic match alignment across different time slices， so that topic information on historical slices was effectively transferred and incorporated into cluster assignment process of the current time slice. Experimental results based on the real-world arXiv evolving textual document dataset demonstrate that compared with the Deep Evolutionary Document Clustering model with Instance-level Mutual Attention Enhancement （DEDC-IMAE）， DETCM achieves an average improvement of 3.08% （-0.37% to 5.43%） in Normalized Mutual Information （NMI） across all time slices， verifying the superior capability of DETCM in tracking topic evolution under dynamic scenarios， enabling more accurate capture of temporal variation features in topics and leading to better clustering performance.

Key words: topic evolution, deep dynamic clustering, representation learning, topic mining, contrastive learning

摘要：

针对现有的深度文档聚类方法在处理动态文档数据时，文档主题随时间演化过程中存在主题混淆和对齐不准确问题，提出一种深度演化主题聚类模型（DETCM）。DETCM可以捕捉动态文档随时间演化的主题信息，结合历史主题信息与当前时间片文档特征，发掘事件主题演化脉络，生成动态文档主题表示。具体来说，为了解决主题随时间演变时的主题混淆问题，设计了基于混合编码器的主题融合学习模块，借助前置时间片的主题信息，加强当前时间片的主题区分度与特征提取。此外，还设计了一种跨时间片的动态主题继承模块，通过将不同时间片上的主题匹配对齐，有效地将历史时间片上的主题信息融入当前时间片的类簇划分过程中。这一设计使得DETCM学习主题时能够继承并借鉴历史时间片的主题信息，有效跟踪动态文本主题持续演化的过程。基于arXiv真实演化文本文档数据集的实验结果表明，相较于深度演化聚类模型DEDC-IMAE （Deep Evolutionary Document Clustering model with Instance-level Mutual Attention Enhancement）， DETCM在所有时间片上的标准化互信息（NMI）指标平均提升了3.08%（-0.37%~5.43%），验证了DETCM在动态场景中具有更好的主题演化追踪能力，能够更准确地捕捉主题的时序变化特征，实现更优的聚类性能。

关键词: 主题演化, 深度动态聚类, 表示学习, 主题挖掘, 对比学习

CLC Number:

TP391.1

Ziyang CHENG, Ruizhang HUANG, Jingjing XUE. Deep evolutionary topic clustering model[J]. Journal of Computer Applications, 2026, 46(1): 85-94.

程梓洋, 黄瑞章, 薛菁菁. 深度演化主题聚类模型[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 85-94.

Figures/Tables 7

References 29

[1]	BAI R， HUANG R， CHEN Y， et al. Deep multi-view document clustering with enhanced semantic embedding ［J］. Information Sciences， 2021， 564： 273-287.
[2]	REN L， QIN Y， CHEN Y， et al. Deep structural enhanced network for document clustering ［J］. Applied Intelligence， 2023， 53（10）： 12163-12178.
[3]	BO D， WANG X， SHI C， et al. Structural deep clustering network ［C］// Proceedings of the Web Conference 2020. New York： ACM， 2020： 1400-1410.
[4]	PENG Z， LIU H， JIA Y， et al. Attention-driven graph clustering network ［C］// Proceedings of the 29th ACM International Conference on Multimedia. New York： ACM， 2021： 935-943.
[5]	XIE J， GIRSHICK R， FARHADI A. Unsupervised deep embedding for clustering analysis ［C］// Proceedings of the 33rd International Conference on Machine Learning. New York： JMLR.org， 2016： 478-487.
[6]	KINGMA D P， WELLING M. Auto-encoding variational Bayes ［EB/OL］. ［2025-03-17］. .
[7]	XU Q， GU H， JI S. Text clustering based on pre-trained models and autoencoders ［J］. Frontiers in Computational Neuroscience， 2024， 17： No.1334436.
[8]	PETUKHOVA A， MATOS-CARVALHO J P， FACHADA N. Text clustering with large language model embeddings ［J］. International Journal of Cognitive Computing in Engineering， 2025， 6： 100-108.
[9]	LU H， CHENG Z， HUANG R， et al. DEDC-IMAE： a deep evolutionary document clustering model with inherited mixed autoencoder ［J］. Information Sciences， 2024， 678： No.120880.
[10]	GERARD P， VOLKOVA S， PENAFIEL L， et al. Modeling information narrative detection and evolution on Telegram during the Russia-Ukraine war ［C］// Proceedings of the 19th International AAAI Conference on Web and Social Media. Palo Alto： AAAI Press， 2025： 602-614.
[11]	LIU K， HE J， CHEN Y. A topic-enhanced Dirichlet model for short text stream clustering ［J］. Neural Computing and Applications， 2024， 36（14）： 8125-8140.
[12]	XU W， LI Y， QIANG J. Dynamic clustering for short text stream based on Dirichlet process ［J］. Applied Intelligence， 2022， 52（4）： 4651-4662.
[13]	GU B， KARGAR S， NAWAB F. Efficient dynamic clustering： capturing patterns from historical cluster evolution ［C］// Proceedings of the 25th International Conference on Extending Database Technology. ［S.l.］： OpenProceedings.org， 2022： 351-363.
[14]	YOU J， HU C， KAMIGAITO H， et al. Robust dynamic clustering for temporal networks ［C］// Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York： ACM， 2021： 2424-2433.
[15]	CHAKRABARTI D， KUMAR R， TOMKINS A. Evolutionary clustering ［C］// Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2006： 554-560.
[16]	CHI Y， SONG X， ZHOU D， et al. Evolutionary spectral clustering by incorporating temporal smoothness ［C］// Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2007： 153-162.
[17]	XU K S， KLIGER M， HERO A O， III. Adaptive evolutionary clustering ［J］. Data Mining and Knowledge Discovery， 2014， 28（2）： 304-336.
[18]	BLEI D M， LAFFERTY J D. Dynamic topic models ［C］// Proceedings of the 23rd International Conference on Machine Learning. New York： ACM， 2006： 113-120.
[19]	JELODAR H， WANG Y， YUAN C， et al. Latent Dirichlet Allocation （LDA） and topic modeling： models， applications， a survey ［J］. Multimedia Tools and Applications， 2019， 78（11）： 15169-15211.
[20]	WANG X， McCALLUM A. Topics over time： a non-Markov continuous-time model of topical trends ［C］// Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2006： 424-433.
[21]	宋凯，陈悦.技术主题动态演化分析的一种新方法： DPL-BMM模型［J］.情报学报， 2024， 43（1）： 25-33.
	SONG K， CHEN Y. New approach for the dynamic evolution analysis of technology topics： DPL-BMM ［J］. Journal of the China Society for Scientific and Technical Information， 2024， 43（1）： 25-33.
[22]	DIENG A B， RUIZ F J R， BLEI D M. Topic modeling in embedding spaces ［J］. Transactions of the Association for Computational Linguistics， 2020， 8： 439-453.
[23]	DIENG A B， RUIZ F J R， BLEI D M. The dynamic embedded topic model ［EB/OL］. ［2025-03-17］. .
[24]	GUO X， GAO L， LIU X， et al. Improved deep embedded clustering with local structure preservation ［C］// Proceedings of the 26th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2017： 1753-1759.
[25]	LIU M， LIU Y， LIANG K， et al. Deep temporal graph clustering ［EB/OL］. ［2025-03-17］. .
[26]	YAN Y， LU N， YAN R. Deep online probability aggregation clustering ［C］// Proceedings of the 2024 European Conference on Computer Vision， LNCS 15111. Cham： Springer， 2025： 37-54.
[27]	CHAZAN S E， GANNOT S， GOLDBERGER J. Deep clustering based on a mixture of autoencoders ［C］// Proceedings of the IEEE 29th International Workshop on Machine Learning for Signal Processing. Piscataway： IEEE， 2019： 1-6.
[28]	MADIRAJU N S， SADAT S M， FISHER D. Deep temporal clustering： fully unsupervised learning of time-domain features ［EB/OL］. ［2025-03-17］. .
[29]	PANTULA P D， MIRIYALA S S， MITRA K. A deep unsupervised learning algorithm for dynamic data clustering ［C］// Proceedings of the 7th Indian Control Conference. Piscataway： IEEE， 2021： 147-152.

数据集	主题数	文档数
数据集	主题数	T1	T2	T3	T4
BBC_evo	5	835	693	556	41
AMiner_evo	3	1 533	943	754	190
Reuters _evo	4	584	4 708	3 765	943
arXiv	3	15 000	15 000	15 000	15 000

数据集	主题数	文档数
数据集	主题数	T1	T2	T3	T4
BBC_evo	5	835	693	556	41
AMiner_evo	3	1 533	943	754	190
Reuters _evo	4	584	4 708	3 765	943
arXiv	3	15 000	15 000	15 000	15 000

数据集	时间片	评价指标	K-means	DTM^［18］	ToT^［20］	DEC^［5］	IDEC^［24］	DEDC-IMAE^［9］	DETCM
BBC_evo	T1	ACC	98.68	40.84	42.28	96.88	97.48	97.12	98.92
		NMI	95.44	50.66	48.07	92.13	92.68	92.90	96.41
		ARI	96.73	32.21	30.05	92.46	93.82	93.09	97.31
	T2	ACC	90.48	40.98	50.51	87.01	90.33	94.09	95.38
		NMI	80.92	32.59	45.41	72.73	74.59	82.43	85.63
		ARI	82.16	11.18	32.14	70.16	76.68	87.29	89.01
	T3	ACC	57.55	30.58	39.75	74.64	76.79	80.76	87.89
		NMI	45.66	12.74	30.07	52.72	53.85	65.51	69.28
		ARI	36.09	5.65	18.02	48.68	50.03	63.76	70.79
	T4	ACC	40.43	32.62	41.84	63.12	63.12	75.17	78.72
		NMI	25.48	7.86	18.46	47.51	48.05	57.92	67.32
		ARI	10.71	2.61	8.77	39.06	38.98	54.90	62.15
AMiner_evo	T1	ACC	97.46	66.01	86.30	95.52	93.32	97.26	97.59
		NMI	88.55	40.19	65.60	87.03	86.13	87.85	89.09
		ARI	92.52	21.96	61.71	90.01	88.15	91.95	92.90
	T2	ACC	94.17	53.66	77.62	92.25	90.66	94.48	95.02
		NMI	77.48	14.84	50.81	73.20	68.35	78.19	81.02
		ARI	82.78	9.46	40.92	77.57	73.42	83.65	85.17
	T3	ACC	71.82	49.73	69.76	85.94	87.40	90.05	92.30
		NMI	44.59	8.66	38.63	54.78	58.36	65.48	71.32
		ARI	43.63	5.24	26.27	61.83	65.34	72.11	77.50
	T4	ACC	51.32	37.37	58.42	72.63	71.05	77.89	78.95
		NMI	33.29	2.30	24.51	34.08	28.15	40.80	47.29
		ARI	27.16	1.25	11.17	36.16	31.63	44.05	45.42
Reuters_evo	T1	ACC	69.69	87.16	92.98	68.32	68.32	69.69	70.03
		NMI	71.42	79.28	83.63	68.01	68.13	71.03	72.50
		ARI	58.17	85.37	88.22	55.34	55.31	58.17	58.91
	T2	ACC	82.05	79.01	70.94	72.53	73.55	76.25	76.47
		NMI	63.81	60.03	58.33	54.35	53.26	60.33	61.60
		ARI	65.61	61.72	56.83	57.13	58.14	61.37	62.07
	T3	ACC	51.47	54.37	61.65	61.72	63.13	64.70	68.15
		NMI	32.21	39.54	45.06	35.65	35.18	47.61	50.83
		ARI	19.17	30.87	32.47	30.63	29.72	41.25	43.00
	T4	ACC	48.78	42.74	67.34	62.21	65.64	69.17	70.91
		NMI	32.46	17.11	47.30	44.08	46.90	49.98	54.03
		ARI	10.62	10.48	41.24	35.44	39.02	42.07	50.67
arXiv	T1	ACC	80.07	55.63	83.00	86.06	85.67	86.16	86.86
		NMI	51.60	21.28	50.82	56.94	55.79	58.00	57.78
		ARI	52.87	19.90	55.78	63.17	62.27	62.91	64.80
	T2	ACC	81.05	59.53	84.38	87.02	86.18	87.89	88.34
		NMI	53.12	36.31	52.93	57.53	55.57	60.75	62.02
		ARI	57.27	35.29	58.77	62.15	61.30	67.06	68.89
	T3	ACC	86.75	60.41	85.17	81.18	86.29	87.53	88.83
		NMI	57.52	30.62	54.18	48.32	58.13	60.20	63.47
		ARI	64.15	32.14	60.49	53.00	63.53	65.92	67.49
	T4	ACC	79.17	63.81	84.34	82.91	84.18	86.37	88.38
		NMI	52.10	40.51	53.79	49.93	55.04	59.08	62.14
		ARI	58.97	40.46	58.59	55.86	60.51	62.87	65.50

数据集	时间片	评价指标	K-means	DTM^［18］	ToT^［20］	DEC^［5］	IDEC^［24］	DEDC-IMAE^［9］	DETCM
BBC_evo	T1	ACC	98.68	40.84	42.28	96.88	97.48	97.12	98.92
		NMI	95.44	50.66	48.07	92.13	92.68	92.90	96.41
		ARI	96.73	32.21	30.05	92.46	93.82	93.09	97.31
	T2	ACC	90.48	40.98	50.51	87.01	90.33	94.09	95.38
		NMI	80.92	32.59	45.41	72.73	74.59	82.43	85.63
		ARI	82.16	11.18	32.14	70.16	76.68	87.29	89.01
	T3	ACC	57.55	30.58	39.75	74.64	76.79	80.76	87.89
		NMI	45.66	12.74	30.07	52.72	53.85	65.51	69.28
		ARI	36.09	5.65	18.02	48.68	50.03	63.76	70.79
	T4	ACC	40.43	32.62	41.84	63.12	63.12	75.17	78.72
		NMI	25.48	7.86	18.46	47.51	48.05	57.92	67.32
		ARI	10.71	2.61	8.77	39.06	38.98	54.90	62.15
AMiner_evo	T1	ACC	97.46	66.01	86.30	95.52	93.32	97.26	97.59
		NMI	88.55	40.19	65.60	87.03	86.13	87.85	89.09
		ARI	92.52	21.96	61.71	90.01	88.15	91.95	92.90
	T2	ACC	94.17	53.66	77.62	92.25	90.66	94.48	95.02
		NMI	77.48	14.84	50.81	73.20	68.35	78.19	81.02
		ARI	82.78	9.46	40.92	77.57	73.42	83.65	85.17
	T3	ACC	71.82	49.73	69.76	85.94	87.40	90.05	92.30
		NMI	44.59	8.66	38.63	54.78	58.36	65.48	71.32
		ARI	43.63	5.24	26.27	61.83	65.34	72.11	77.50
	T4	ACC	51.32	37.37	58.42	72.63	71.05	77.89	78.95
		NMI	33.29	2.30	24.51	34.08	28.15	40.80	47.29
		ARI	27.16	1.25	11.17	36.16	31.63	44.05	45.42
Reuters_evo	T1	ACC	69.69	87.16	92.98	68.32	68.32	69.69	70.03
		NMI	71.42	79.28	83.63	68.01	68.13	71.03	72.50
		ARI	58.17	85.37	88.22	55.34	55.31	58.17	58.91
	T2	ACC	82.05	79.01	70.94	72.53	73.55	76.25	76.47
		NMI	63.81	60.03	58.33	54.35	53.26	60.33	61.60
		ARI	65.61	61.72	56.83	57.13	58.14	61.37	62.07
	T3	ACC	51.47	54.37	61.65	61.72	63.13	64.70	68.15
		NMI	32.21	39.54	45.06	35.65	35.18	47.61	50.83
		ARI	19.17	30.87	32.47	30.63	29.72	41.25	43.00
	T4	ACC	48.78	42.74	67.34	62.21	65.64	69.17	70.91
		NMI	32.46	17.11	47.30	44.08	46.90	49.98	54.03
		ARI	10.62	10.48	41.24	35.44	39.02	42.07	50.67
arXiv	T1	ACC	80.07	55.63	83.00	86.06	85.67	86.16	86.86
		NMI	51.60	21.28	50.82	56.94	55.79	58.00	57.78
		ARI	52.87	19.90	55.78	63.17	62.27	62.91	64.80
	T2	ACC	81.05	59.53	84.38	87.02	86.18	87.89	88.34
		NMI	53.12	36.31	52.93	57.53	55.57	60.75	62.02
		ARI	57.27	35.29	58.77	62.15	61.30	67.06	68.89
	T3	ACC	86.75	60.41	85.17	81.18	86.29	87.53	88.83
		NMI	57.52	30.62	54.18	48.32	58.13	60.20	63.47
		ARI	64.15	32.14	60.49	53.00	63.53	65.92	67.49
	T4	ACC	79.17	63.81	84.34	82.91	84.18	86.37	88.38
		NMI	52.10	40.51	53.79	49.93	55.04	59.08	62.14
		ARI	58.97	40.46	58.59	55.86	60.51	62.87	65.50

时间片	评价指标	DTCM		DETCM
时间片	评价指标	无类簇对比	有类簇对比	线性融合	无类簇对比	有类簇对比
T1	ACC	98.92	98.92	96.28	98.92	98.92
	NMI	96.41	96.41	90.99	96.41	96.41
	ARI	97.31	97.31	90.83	97.31	97.31
T2	ACC	90.47	91.21	89.75	94.80	95.38
	NMI	74.42	78.93	76.29	84.57	85.63
	ARI	77.83	80.66	79.41	87.96	89.01
T3	ACC	77.51	78.17	81.11	85.43	87.89
	NMI	51.21	54.33	64.55	66.59	69.28
	ARI	54.93	55.40	64.06	69.05	70.79
T4	ACC	60.99	65.95	67.37	70.17	78.72
	NMI	44.94	48.03	53.89	54.00	67.32
	ARI	40.01	41.65	48.56	52.94	62.15

Deep evolutionary topic clustering model

深度演化主题聚类模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 29

Related Articles 15

Recommended Articles

Metrics

论文领域	T1	T2	T3	T4
物理	equation solution theory brane gauge field quark decay cloaking microstructure	superconducting decay field mass theory gauge cloaking wettability pluripolar photon	energy quantum field theory equation decay mass quark gauge spectrum	higgs quantum spectrum decay mass particle quark photon wave energy
计算机科学	algorithm reranker network code channel lut propose selection scheme channel	encoding channel network precoding datum method propose learning model wiretapper	algorithm image network method propose control datum task efficient model	model datum code learning language network performance algorithm propose multimodal
数学	algebra euler graphon homotopically nll find discovery gevrey contractile prove	equation algebra prove subgroup approximation approach solution isometry continuous vertex	algebra group graphon triangulate homotopically prove compact subgroup inequality space	equation solution problem choquet algorithm nonlinear prove algebra system inequality

方法	耗时/s
K-means	6.31
DTM^［18］	452.34
ToT^［20］	23.70
DEC^［5］	29.31
IDEC^［24］	30.19
DEDC-IMAE^［9］	266.30
DTCM（无类簇对比）	306.83
DTCM	176.82
DETCM（无类簇对比）	393.89
DETCM（线性融合）	415.03
DETCM	500.66

[1]	Wen LI, Kairong LI, Kai YANG. Subgraph-aware contrastive learning with data augmentation [J]. Journal of Computer Applications, 2026, 46(1): 1-9.
[2]	Xingyao YANG, Zheng QI, Jiong YU, Zulian ZHANG, Shuai MA, Hongtao SHEN. Session-based recommendation model based on time-aware and space-enhanced dual channel graph neural network [J]. Journal of Computer Applications, 2026, 46(1): 104-112.
[3]	Zhixiong XU, Bo LI, Xiaoyong BIAN, Qiren HU. Adversarial sample embedded attention U-Net for 3D medical image segmentation [J]. Journal of Computer Applications, 2025, 45(9): 3011-3016.
[4]	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.
[5]	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.
[6]	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.
[7]	Zhiyuan WANG, Tao PENG, Jie YANG. Integrating internal and external data for out-of-distribution detection training and testing [J]. Journal of Computer Applications, 2025, 45(8): 2497-2506.
[8]	Jin XIE, Surong CHU, Yan QIANG, Juanjuan ZHAO, Hua ZHANG, Yong GAO. Dual-branch distribution consistency contrastive learning model for hard negative sample identification in chest X-rays [J]. Journal of Computer Applications, 2025, 45(7): 2369-2377.
[9]	Zhenzhou WANG, Fangfang GUO, Jingfang SU, He SU, Jianchao WANG. Robustness optimization method of visual model for intelligent inspection [J]. Journal of Computer Applications, 2025, 45(7): 2361-2368.
[10]	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.
[11]	Mingfeng YU, Yongbin QIN, Ruizhang HUANG, Yanping CHEN, Chuan LIN. Multi-label text classification method based on contrastive learning enhanced dual-attention mechanism [J]. Journal of Computer Applications, 2025, 45(6): 1732-1740.
[12]	Wenjing YAN, Ruidong WANG, Min ZUO, Qingchuan ZHANG. Recipe recommendation model based on hierarchical learning of flavor embedding heterogeneous graph [J]. Journal of Computer Applications, 2025, 45(6): 1869-1878.
[13]	Chaoying JIANG, Qian LI, Ning LIU, Lei LIU, Lizhen CUI. Readmission prediction model based on graph contrastive learning [J]. Journal of Computer Applications, 2025, 45(6): 1784-1792.
[14]	Wenbin HU, Tianxiang CAI, Tianle HAN, Zhaoman ZHONG, Changxia MA. Multimodal sarcasm detection model integrating contrastive learning with sentiment analysis [J]. Journal of Computer Applications, 2025, 45(5): 1432-1438.
[15]	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.