A KAN-CTR Prediction Model Integrating Hybrid Community and Cluster-Level Feature

QIAN Zhongsheng; RAO Yuxian; WU Minxuan; PENG Shaoqiang; WANG Rongrong; XU Kewen

doi:10.12263/DZXB.20250993

您当前的位置：

首页 >

文章列表页 >

A KAN-CTR Prediction Model Integrating Hybrid Community and Cluster-Level Feature

PAPERS | 更新时间：2026-06-04

- A KAN-CTR Prediction Model Integrating Hybrid Community and Cluster-Level Feature
- ACTA ELECTRONICA SINICA Vol. 54, Issue 1, Pages: 395-416(2026)
- 作者机构：
  
  江西财经大学计算机与人工智能学院，江西南昌 330013
- 作者简介：
- 基金信息：
  
  Foundation Item(s):　Foundation Item(s): National Natural Science Foundation of China(62262025);Jiangxi Poyang Support Program for Talents of China-Major Discipline Academic and Technical Leaders Training Program of Jiangxi Province-Leading Talent (Academic)(20243BCE51024)
- DOI：10.12263/DZXB.20250993
  CLC： TP399;
- Received：10 January 2026，
  
  Accepted：23 January 2026，
  
  Published：25 January 2026
- 稿件说明：
移动端阅览
钱忠胜, 饶雨贤, 吴敏璇, 等. 融合混合社区与簇级特征的KAN-CTR预测模型[J]. 电子学报, 2026, 54(01): 395-416.

QIAN Zhongsheng, RAO Yuxian, WU Minxuan, et al. A KAN-CTR Prediction Model Integrating Hybrid Community and Cluster-Level Feature[J]. Acta Electronica Sinica, 2026, 54(01): 395-416.
钱忠胜, 饶雨贤, 吴敏璇, 等. 融合混合社区与簇级特征的KAN-CTR预测模型[J]. 电子学报, 2026, 54(01): 395-416. DOI：10.12263/DZXB.20250993

QIAN Zhongsheng, RAO Yuxian, WU Minxuan, et al. A KAN-CTR Prediction Model Integrating Hybrid Community and Cluster-Level Feature[J]. Acta Electronica Sinica, 2026, 54(01): 395-416. DOI：10.12263/DZXB.20250993

摘要

点击率（Click-Through Rate， CTR）预测是推荐系统的核心任务，其目标是通过用户历史行为与项目特征建模，预测用户对候选项目产生点击行为的概率。然而，现有CTR方法在建模全局交互结构、提取多跳邻居信息及提升高维特征交互学习效率等方面仍存在问题。用户与项目之间的交互通常呈现多层次、强结构化的关联特征，若直接建模则计算量过大且难以捕捉不同层级邻域之间的语义关系，从而限制对潜在语义关联与用户偏好的深入挖掘，而且现有CTR模型多依赖传统神经网络的固定激活函数，在建模高阶非线性特征交互时灵活性不足，易出现特征冗余、泛化能力弱等问题，导致预测精度难以进一步提升。针对这些问题，提出一种融合混合社区划分与簇级特征提取的Kolmogorov-Arnold Networks（KAN）架构CTR预测模型（A KAN-CTR prediction model integrating Hybrid Community and Cluster-level Feature， HCCF-KCTR）。首先，设计一种层次化的混合社区聚类策略，结合粗粒度的全局社区划分与细粒度的簇内优化，将复杂的全局交互关系解构为结构清晰、语义连贯的簇级单元，在保留关键结构信息的同时显著降低建模复杂度。其次，基于全局社区划分结果对多跳邻居进行簇级映射，并引入簇感知注意力池化机制（Attention Pooling），动态评估每跳邻居在簇内及簇间的语义重要性，自适应分配注意力权重，生成高质量的多跳邻居簇级嵌入表示，以充分捕捉用户与项目间的多层次交互特征。最后，利用KAN网络可学习函数替代固定激活函数，构建多个跨跳跨簇特征组合，将复杂的多跳交互特征转化为可解释的低阶函数组合表达，实现结构信息与语义特征的深度融合，进一步提升模型的预测精度与表达能力。在MovieLens、Electronics、Book及Taobao四个真实数据集上与13种主流CTR模型进行对比，实验结果表明，在AUC、GAUC和LogLoss这3个指标上，所提模型HCCF-KCTR相对已有最优基线模型分别平均最少提升2.74%、2.19%、3.68%，验证了其在特征交互建模与预测方面的优越性。此外，本文还通过消融实验、参数敏感性实验以及模型效率实验，验证了各模块的必要性、协同有效性，以及模型在整体效率上的均衡性，进一步阐明了模型具有良好的泛化能力。

Abstract

click-through rate (CTR) prediction is a core task in recommendation systems

whose goal is to predict the probability that a user will click on a candidate item by modeling the user’s historical behaviors and item features. However

existing CTR methods still have problems in modeling global interaction structures

extracting multi-hop neighbor information

and improving the efficiency of high-dimensional feature interaction learning. The interactions between users and items usually exhibit multi-level and strongly structured association characteristics; direct modeling will lead to excessive computational complexity and difficulty in capturing the semantic relationships between different levels of neighborhoods

thereby limiting the in-depth exploration of potential semantic associations and user preferences. Moreover

most existing CTR models rely on fixed activation functions of traditional neural networks

which lack flexibility in modeling high-order nonlinear feature interactions

and are prone to problems such as feature redundancy and weak generalization ability

resulting in difficulty in further improving prediction accuracy. To address these problems

this paper proposes a kolmogorov-arnold networks (KAN)-based CTR prediction model integrating hybrid community division and cluster-level feature extraction (HCCF-KCTR). Firstly

a hierarchical hybrid community clustering strategy is designed

which combines coarse-grained global community division and fine-grained intra-cluster optimization to decompose complex global interaction relationships into cluster-level units with clear structure and coherent semantics. This strategy significantly reduces the modeling complexity while retaining key structural information. Secondly

based on the results of global community division

multi-hop neighbors are mapped at the cluster level

and a cluster-aware attention pooling mechanism is introduced to dynamically evaluate the semantic importance of each hop of neighbors within and between clusters

adaptively assign attention weights

and generate high-quality cluster-level embedding representations of multi-hop neighbors

so as to fully capture the multi-level interaction characteristics between users and items. Finally

the learnable function of the KAN network is used to replace the fixed activation function

and multiple cross-hop and cross-cluster feature combinations are constructed to convert complex multi-hop interaction features into interpretable low-order function combination

realizing the in-depth fusion of structural information and semantic features

and further improving the prediction accuracy and expressive ability of the model. Comparative experiments are conducted with 13 mainstream CTR models on four real-world datasets

namely MovieLens

Electronics

Book

and Taobao. The experimental results show that

in terms of the three metrics of AUC

GAUC

and LogLoss

the proposed HCCF-KCTR model achieves an average minimum improvement of 2.74%

2.19%

and 3.68% respectively compared with the existing optimal baseline model

verifying its superiority in feature interaction modeling and prediction. In addition

this work verifies the necessity and synergistic effectiveness of each module as well as the balance of the model in overall efficiency through ablation experiments

parameter sensitivity experiments and model efficiency experiments

further demonstrating that the model has excellent generalization ability.

关键词

Keywords

references

Yang Yanwu , Zhai Panyu . Click-through rate prediction in online advertising: A literature review [J ] . Information Processing & Management , 2022 , 59 ( 2 ): 102853 . DOI: 10.1016/j.ipm.2021.102853 http://dx.doi.org/10.1016/j.ipm.2021.102853

Zhang Weinan , Qin Jiarui , Guo Wei , et al . Deep learning for click-through rate estimation [C ] // Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence Organization , 2021 : 4695 - 4703 . DOI: 10.24963/ijcai.2021/636 http://dx.doi.org/10.24963/ijcai.2021/636

He Xiangnan , Deng Kuan , Wang Xiang , et al . Lightgcn: Simplifying and powering graph convolution network for recommendation [C ] // Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2020 : 639 - 648 . DOI: 10.1145/3397271.3401063 http://dx.doi.org/10.1145/3397271.3401063

Fan Wenqi , Ma Yao , Li Qing , et al . Graph neural networks for social recommendation [C ] // The World Wide Web Conference . New York : ACM , 2019 : 417 - 426 . DOI: 10.1145/3308558.3313488 http://dx.doi.org/10.1145/3308558.3313488

Wang Xiang , He Xiangnan , Wang Meng , et al . Neural graph collaborative filtering [C ] // Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2019 : 165 - 174 . DOI: 10.1145/3331184.3331267 http://dx.doi.org/10.1145/3331184.3331267

Guo Zhiqiang , Li Jianjun , Li Guohui , et al . LGMRec: Local and global graph learning for multimodal recommendation [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2024 , 38 ( 8 ): 8454 - 8462 . DOI: 10.1609/aaai.v38i8.28688 http://dx.doi.org/10.1609/aaai.v38i8.28688

Liu Qiao , Zeng Yifu , Mokhosi R , et al . STAMP: Short-term attention/memory priority model for session-based recommendation [C ] // Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2018 : 1831 - 1839 . DOI: 10.1145/3219819.3219950 http://dx.doi.org/10.1145/3219819.3219950

Sun Jianing , Zhang Yingxue , Guo Wei , et al . Neighbor interaction aware graph convolution networks for recommendation [C ] // Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2020 : 1289 - 1298 . DOI: 10.1145/3397271.3401123 http://dx.doi.org/10.1145/3397271.3401123

Guo Huifeng , Tang Ruiming , Ye Yunming , et al . DeepFM: A factorization-machine based neural network for CTR prediction [C ] // Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence Organization , 2017 : 1725 - 1731 . DOI: 10.24963/ijcai.2017/239 http://dx.doi.org/10.24963/ijcai.2017/239

Zhou Guorui , Mou Na , Fan Ying , et al . Deep interest evolution network for click-through rate prediction [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2019 , 33 ( 1 ): 5941 - 5948 . DOI: 10.1609/aaai.v33i01.33015941 http://dx.doi.org/10.1609/aaai.v33i01.33015941

Lian Jianxun , Zhou Xiaohuan , Zhang Fuzheng , et al . xDeepFM: Combining explicit and implicit feature interactions for recommender systems [C ] // Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2018 : 1754 - 1763 . DOI: 10.1145/3219819.3220023 http://dx.doi.org/10.1145/3219819.3220023

黄若然 , 崔莉 , 韩传奇 . 推荐系统中稀疏情景预测的特征-类别交互因子分解机 [J ] . 计算机研究与发展 , 2022 , 59 ( 7 ): 1553 - 1568 .

Huang Ruoran , Cui Li , Han Chuanqi . Feature-over-field interaction factorization machine for sparse contextualized prediction in recommender systems [J ] . Journal of Computer Research and Development , 2022 , 59 ( 7 ): 1553 - 1568 . (in Chinese)

Zhou Guorui , Zhu Xiaoqiang , Song Chengru , et al . Deep interest network for click-through rate prediction [C ] // Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM , 2018 : 1059 - 1068 . DOI: 10.1145/3219819.3219823 http://dx.doi.org/10.1145/3219819.3219823

Wang Ruoxi , Fu Bin , Fu Gang , et al . Deep & cross network for ad click predictions [C ] // Proceedings of the ADKDD’17 . New York : ACM , 2017 : 1 - 7 . DOI: 10.1145/3124749.3124754 http://dx.doi.org/10.1145/3124749.3124754

Liu Ziming , Wang Yixuan , Vaidya S , et al . KAN: Kolmogorov-Arnold networks [PP/OL ] . V5.arXiv ( 2025-02-09 )[ 2026-01-10 ] . https://doi.org/10.48550/arXiv.2404.19756 https://doi.org/10.48550/arXiv.2404.19756 .

Hao Pengyi , Qian Zhaojie , Wang Shuang , et al . Community aware graph embedding learning for item recommendation [J ] . World Wide Web , 2023 , 26 ( 6 ): 4093 - 4108 . DOI: 10.1007/s11280-023-01224-5 http://dx.doi.org/10.1007/s11280-023-01224-5

邱林山 , 房子荃 , 陈璐 , 等 . 面向异质信息网络的双通道协同聚类算法 [J ] . 计算机学报 , 2023 , 46 ( 11 ): 2416 - 2430 .

Qiu Linshan , Fang Ziquan , Chen Lu , et al . A bi-channel co-clustering algorithm for heterogeneous information networks [J ] . Chinese Journal of Computers , 2023 , 46 ( 11 ): 2416 - 2430 . (in Chinese)

Fortunato S , Hric D . Community detection in networks: A user guide [J ] . Physics Reports , 2016 , 659 : 1 - 44 . DOI: 10.1016/j.physrep.2016.09.002 http://dx.doi.org/10.1016/j.physrep.2016.09.002

钱忠胜 , 王亚惠 , 俞情媛 , 等 . 利用伪重叠判定机制的多层循环GCN跨域推荐 [J ] . 软件学报 , 2025 , 36 ( 9 ): 4327 - 4348 .

Qian Zhongsheng , Wang Yahui , Yu Qingyuan , et al . Multi-layer recurrent GCN cross-domain recommendation with pseudo-overlap detection mechanism [J ] . Journal of Software , 2025 , 36 ( 9 ): 4327 - 4348 . (in Chinese)

Hu Fenyu , Zhu Yanqiao , Wu Shu , et al . Hierarchical graph convolutional networks for semi-supervised node classification [C ] // Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence Organization , 2019 : 4532 - 4539 . DOI: 10.24963/ijcai.2019/630 http://dx.doi.org/10.24963/ijcai.2019/630

Chen Hong , Huang Bin , Wang Xin , et al . Global-local GraphFormer: Towards better understanding of user intentions in sequential recommendation [C ] // Proceedings of the 5th ACM International Conference on Multimedia in Asia . New York : ACM , 2024 : 1 - 7 . DOI: 10.1145/3595916.3626377 http://dx.doi.org/10.1145/3595916.3626377

钱忠胜 , 黄恒 , 万子珑 . 融合自注意力机制的多行为图对比学习推荐方法 [J ] . 电子学报 , 2024 , 52 ( 11 ): 3684 - 3698 .

Qian Zhongsheng , Huang Heng , Wan Zilong . The multi-behavior graph contrastive learning recommendation method with self-attention mechanism [J ] . Acta Electronica Sinica , 2024 , 52 ( 11 ): 3684 - 3698 . (in Chinese)

李邵莹 , 孟丹 , 孔超 , 等 . 面向社交推荐的自适应高阶隐式关系建模 [J ] . 软件学报 , 2023 , 34 ( 10 ): 4851 - 4869 .

Li Shaoing , Meng Dan , Kong Chao , et al . Adaptive high-order implicit relations modeling for social recommendation [J ] . Journal of Software , 2023 , 34 ( 10 ): 4851 - 4869 . (in Chinese)

Wu Chuhan , Wu Fangzhao , Huang Yongfeng , et al . User-as-graph: User modeling with heterogeneous graph pooling for news recommendation [C ] // Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence Organization , 2021 : 1624 - 1630 . DOI: 10.24963/ijcai.2021/224 http://dx.doi.org/10.24963/ijcai.2021/224

Hou Zhenyu , Liu Xiao , Cen YuKuo , et al . GraphMAE: Self-supervised masked graph autoencoders [C ] // Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining . New York : ACM , 2022 : 594 - 604 . DOI: 10.1145/3534678.3539321 http://dx.doi.org/10.1145/3534678.3539321

Guo Kan , Hu Yongli , SunYanfeng , et al . Hierarchical graph convolution network for traffic forecasting [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2021 , 35 ( 1 ): 151 - 159 . DOI: 10.1609/aaai.v35i1.16088 http://dx.doi.org/10.1609/aaai.v35i1.16088

陈荣元 , 文杰彬 , 黄少年 , 等 . 基于邻域与超图协作的会话推荐 [J ] . 电子学报 , 2025 , 53 ( 8 ): 2805 - 2817 .

Chen Rongyuan , Wen Jiebin , Huang Shaonian , et al . Neighborhood and hypergraph collaboration for session-based recommendation [J ] . Acta Electronica Sinica , 2025 , 53 ( 8 ): 2805 - 2817 . (in Chinese)

Rendle S . Factorization machines [C ] // 2010 IEEE International Conference on Data Mining . Piscataway : IEEE , 2010 : 995 - 1000 . DOI: 10.1109/icdm.2010.127 http://dx.doi.org/10.1109/icdm.2010.127

Qu Yanru , Cai Han , Ren Kan , et al . Product-based neural networks for user response prediction [C ] // 2016 IEEE 16th International Conference on Data Mining . Piscataway : IEEE , 2016 : 1149 - 1154 . DOI: 10.1109/icdm.2016.0151 http://dx.doi.org/10.1109/icdm.2016.0151

Xiao Jun , Ye Hao , He Xiangnan , et al . Attentional factorization machines: Learning the weight of feature interactions via attention networks [C ] // Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence . International Joint Conferences on Artificial Intelligence Organization , 2017 : 3119 - 3125 . DOI: 10.24963/ijcai.2017/435 http://dx.doi.org/10.24963/ijcai.2017/435

Song Weiping , Shi Chence , Xiao Zhiping , et al . AutoInt: Automatic feature interaction learning via self-attentive neural networks [C ] // Proceedings of the 28th ACM International Conference on Information and Knowledge Management . New York : ACM , 2019 : 1161 - 1170 . DOI: 10.1145/3357384.3357925 http://dx.doi.org/10.1145/3357384.3357925

Wang Lei , Zhang Songheng , Wang Yun , et al . LLM4Vis: Explainable visualization recommendation using ChatGPT [PP/OL ] . V2.arXiv ( 2023-10-16 )[ 2026-01-10 ] . https://doi.org/10.48550/arXiv.2310.07652 https://doi.org/10.48550/arXiv.2310.07652 .

Zhang Songheng , Li Haotian , Qu Huamin , et al . AdaVis: Adaptive and explainable visualization recommendation for tabular data [J ] . IEEE Transactions on Visualization and Computer Graphics , 2024 , 30 ( 9 ): 5923 - 5938 . DOI: 10.1109/tvcg.2023.3316469 http://dx.doi.org/10.1109/tvcg.2023.3316469

Wang Kefan , Wang Hao , Guo Wei , et al . DLF: Enhancing explicit-implicit interaction via dynamic low-order-aware fusion for CTR prediction [C ] // Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2025 : 2213 - 2223 . DOI: 10.1145/3726302.3729956 http://dx.doi.org/10.1145/3726302.3729956

Dilbaz S , Saribas H . STEC: See-through transformer-based encoder for CTR prediction [C ] // 2025 IEEE 4th International Conference on Computing and Machine Intelligence . Piscataway : IEEE , 2025 : 1 - 7 . DOI: 10.1109/icmi65310.2025.11141335 http://dx.doi.org/10.1109/icmi65310.2025.11141335

Han Ruidong , Li Qianzhong , Jiang He , et al . Enhancing CTR prediction through sequential recommendation pre-training: Introducing the SRP4CTR framework [C ] // Proceedings of the 33rd ACM International Conference on Information and Knowledge Management . New York : ACM , 2024 : 3777 - 3781 . DOI: 10.1145/3627673.3679914 http://dx.doi.org/10.1145/3627673.3679914

Shi Yunxiao , Xu Wujiang , Zhang Haimin , et al . Beyond KAN: Introducing KarSein for adaptive high-order feature interaction modeling in CTR prediction [PP/OL ] . V6.arXiv ( 2025-12-04 )[ 2026-01-10 ] . https://doi.org/10.48550/arXiv.2408.08713 https://doi.org/10.48550/arXiv.2408.08713 .

Murniyati , Mutiara A B , Wirawan S , et al . Expanding Louvain algorithm for clustering relationship formation [J ] . International Journal of Advanced Computer Science and Applications , 2023 , 14 ( 1 ). DOI: 10.14569/ijacsa.2023.0140177 http://dx.doi.org/10.14569/ijacsa.2023.0140177

Bei Yuanchen , Chen Hao , Chen Shengyuan , et al . Non-recursive cluster-scale graph interacted model for click-through rate prediction [C ] // Proceedings of the 32nd ACM International Conference on Information and Knowledge Management . New York : ACM , 2023 : 3748 - 3752 . DOI: 10.1145/3583780.3615180 http://dx.doi.org/10.1145/3583780.3615180

Chang Jianxin Zhang Chenbin , Fu Zhiyi , et al . TWIN: TWo-stage interest network for lifelong user behavior modeling in CTR prediction at Kuaishou [C ] // Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining . New York : ACM , 2023 : 3785 - 3794 . DOI: 10.1145/3580305.3599922 http://dx.doi.org/10.1145/3580305.3599922

Kang Yu , Pan Junwei , Jin Jipeng , et al . Towards unifying feature interaction models for click-through rate prediction [M ] // Machine Learning and Knowledge Discovery in Databases . Research Track. ChamSpringer Nature Switzerland, 2025 : 451 - 467 . DOI: 10.1007/978-3-032-06096-9_26 http://dx.doi.org/10.1007/978-3-032-06096-9_26

Song Xin , Li Xiaochen , Hu Jinxin , et al . LREA: Low-rank efficient attention on modeling long-term user behaviors for CTR prediction [C ] // Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval . New York : ACM , 2025 : 2843 - 2847 . DOI: 10.1145/3726302.3730228 http://dx.doi.org/10.1145/3726302.3730228

Qi Pi , Zhou Guorui , Zhang Yujing , et al . Search-based user interest modeling with lifelong sequential behavior data for click-through rate prediction [C ] // Proceedings of the 29th ACM International Conference on Information & Knowledge Management . New York : ACM , 2020 : 2685 - 2692 . DOI: 10.1145/3340531.3412744 http://dx.doi.org/10.1145/3340531.3412744

Xu Xiang , Wang Hao , Guo Wei , et al . Multi-granularity interest retrieval and refinement network for long-term user behavior modeling in CTR prediction [C ] // Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1 . New York : ACM , 2025 : 2745 - 2755 . DOI: 10.1145/3690624.3709438 http://dx.doi.org/10.1145/3690624.3709438

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

The Multi-Behavior Graph Contrastive Learning Recommendation Method with Self-Attention Mechanism

Self-Supervised Learning for Alleviating Popularity Bias in Recommender Systems

Research on Privacy-Preserving Two-Party Collaborative Filtering Recommendation

Anti-Attack Recommender Algorithm Based on Automatic Trust Establishment

Spatial-FineDef: An Approach for Detecting Small Defects in Wind Turbine Blades that Integrate Multi-Scale Perception and Adaptive Enhancement

Related Author

QIAN Zhong-sheng

HUANG Heng

WAN Zi-long

ZHANG Shuai

GAO Min

WEN Jun-hao

XIONG Qing-yu

TANG Xu

Related Institution

School of Computer and Artificial Intelligence, Jiangxi University of Finance & Economics

Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University), Ministry of Education

School of Big Data & Software Engineering, Chongqing University

Guangdong Key Laboratory of Information Security TechnologySun Yat-sen UniversityGuangzhouGuangdong 510275China

Software SchoolSun Yat-sen UniversityGuangzhouGuangdong 510275China

⁰