计算机科学 ›› 2022, Vol. 49 ›› Issue (11): 109-116.doi: 10.11896/jsjkx.210900101
富坤, 郭云朋, 禚佳明, 李佳宁, 刘琪
FU Kun, GUO Yun-peng, ZHUO Jia-ming, LI Jia-ning, LIU Qi
摘要： 在网络表示学习的研究中,数据的不完整性问题是一个重要问题,该问题使现有的表示学习算法难以达到预期效果。近年来,不少学者针对此类问题提出了解决方法,这些方法大多仅考虑标签信息本身的缺失问题,对数据不平衡性涉及较少,尤其是某一类别标签完全缺失的完全不平衡问题。解决这类问题的学习算法并不完善,主要存在的问题是在聚合邻域特征时侧重于考虑网络结构信息,未利用属性特征与语义特征间的关系来增强表示结果。为了解决以上问题,提出了融合属性特征与结构特征的SECT(Semantic Information Enhanced Network Embedding with Completely Imbalanced Labels)方法。首先,在考虑属性空间和语义空间关系的基础上,引入注意力机制进行监督学习,得到语义信息向量;然后,应用变分自编码器无监督提取结构特征以增强算法的鲁棒性;最后,在嵌入空间中融合语义与结构两种信息。将使用SECT算法得到的网络向量表示在Cora,Citeseer等数据集上进行测试,应用于节点分类任务时与RECT和GCN等算法相比,取得了0.86%~1.97%的效果提升。网络向量表示的可视化结果显示,与其他算法相比,SECT算法的类间距离变大,类簇内部更加紧凑,能较清晰地区分类别边界。实验结果表明了SECT算法的有效性,SECT得益于更好地在低维嵌入空间中融合语义信息,有效提升了存在完全不平衡标签情况下的节点分类任务性能。
中图分类号:
| [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]YIN Y,JI L X,HUANG R Y,et al.Research and developmentof network representation learning [J].Chinese Journal of Network and Information Security,2019,5(2):77-87. [3]BALASUBRAMANIAN M,SCHWARTZ E L.The isomap algorithm and topological stability[J].Science,2002,295(5552):7. [4]ROWEIS S T,SAUL L K.Nonlinear dimensionality reduction by locally linear embedding [J].Science,2000:290(5500):2323-2326. [5]BELKIN M,NIYOGI P.Laplacian eigenmaps and spectral techniques for embedding and clustering[C]//Proceedings of the 2001 14th International Conference on Neural Information Processing Systems:Natural and Synthetic.Cambridge,MA:MIT Press,2001:585-591. [6]PEROZZI B,ALRFOU R,SKIENA S.Deepwalk:online learningof social representations[C]//Proceedings of the 20th ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2014:701-710. [7]GROVER A,LESKOVEC J.node2vec:Scalable feature lear-ning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM,2016:855-864. [8]TANG J,QU M,WANG M,et al.LINE:large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web.New York:ACM,2015:1067-1077. [9]CAO S,LU W,XU Q.Grarep:learning graph representations with global structural information[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.New York:ACM,2015:891-900. [10]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[C]//International Conference on Learning Representations(ICLR).2017. [11]HAMILTON W L,YING R,LESKOVEC J.Inductive representation learning on large graphs[C]//Neural Information Processing Systems(NIPS).2017:1024-1034. [12]PETAR V,GUILLEM C,ARANTXA C,et al.Graph attention networks [C]//Proceedings of the 6th International Conference on Learning Representations.Vancouver,BC:Elsevier,2018:1-12. [13]KLICPERA J,BOJCHEVSKI A,GUNNEMANN S.Predictthen propagate:Graph neural networks meet personalized page-rank[C]//International Conference on Learning Representations.2019. [14]WANG Z,YE X J,WANG C K,et al.Network Embedding with Completely-imbalanced Labels[J].IEEE Transactions on Know-ledge and Data Engineering(TKDE),2020,33(11):3634-3647. [15]MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[C]//International Conference on Learning Representations(ICLR).2013. [16]MNIH A,HINTON G E.A scalable hierarchical distributed lan-guage model[C]//Advances in Neural Information Processing Systems.2009:1081-1088. [17]MORIN F,BENGIO Y.Hierarchical probabilisticneural network language model[C]//Proceedings of the International Workshop on Artificial Intelligence and Statistics.2005:246-252. [18]YANG C,LIU Z Y,ZHAO D L,et al.Network representation learning with rich text information[C]//Proceedings of IJCAI.2015. [19]KIPF T N,WELLING M.Variational graph auto-encoders[C]//NIPS Workshop on Bayesian Deep Learning.2016. [20]KINGMA D P,WELLING M.Auto-encoding variational bayes[C]//Proceedings of the International Conference on Learning Representations(ICLR).2014. [21]BOUSQUETO,ELISSEEFF A.Stability and generalization [J].Journal of Machine Learning Research,2002,2(Mar):499-526. [22]ZHOU Z H,WANG W,GAO W,et al.Introduction to the theory of Machine Learning[M].Beijing:China Machie Press(CMP),2020:92-94. [23]STUDENT.The Probable Error of a Mean[J].Biometrika,1908,6(1):1-25. |
| [1] | 王冠宇, 钟婷, 冯宇, 周帆. 基于矢量量化编码的协同过滤推荐方法 Collaborative Filtering Recommendation Method Based on Vector Quantization Coding 计算机科学, 2022, 49(9): 48-54. https://doi.org/10.11896/jsjkx.210700109 |
| [2] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
| [3] | 史殿习, 赵琛然, 张耀文, 杨绍武, 张拥军. 基于多智能体强化学习的端到端合作的自适应奖励方法 Adaptive Reward Method for End-to-End Cooperation Based on Multi-agent Reinforcement Learning 计算机科学, 2022, 49(8): 247-256. https://doi.org/10.11896/jsjkx.210700100 |
| [4] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
| [5] | 李勇, 吴京鹏, 张钟颖, 张强. 融合快速注意力机制的节点无特征网络链路预测算法 Link Prediction for Node Featureless Networks Based on Faster Attention Mechanism 计算机科学, 2022, 49(4): 43-48. https://doi.org/10.11896/jsjkx.210800276 |
| [6] | 杨辉, 陶力宏, 朱建勇, 聂飞平. 基于锚点的快速无监督图嵌入 Fast Unsupervised Graph Embedding Based on Anchors 计算机科学, 2022, 49(4): 116-123. https://doi.org/10.11896/jsjkx.210200098 |
| [7] | 唐雨潇, 王斌君. 基于深度生成模型的人脸编辑研究进展 Research Progress of Face Editing Based on Deep Generative Model 计算机科学, 2022, 49(2): 51-61. https://doi.org/10.11896/jsjkx.210400108 |
| [8] | 蒋宗礼, 樊珂, 张津丽. 基于生成对抗网络和元路径的异质网络表示学习 Generative Adversarial Network and Meta-path Based Heterogeneous Network Representation Learning 计算机科学, 2022, 49(1): 133-139. https://doi.org/10.11896/jsjkx.201000179 |
| [9] | 张仁杰, 陈伟, 杭梦鑫, 吴礼发. 基于变分自编码器的不平衡样本异常流量检测 Detection of Abnormal Flow of Imbalanced Samples Based on Variational Autoencoder 计算机科学, 2021, 48(7): 62-69. https://doi.org/10.11896/jsjkx.200600022 |
| [10] | 曾伟良, 陈漪皓, 姚若愚, 廖睿翔, 孙为军. 时空图注意力网络在交叉口车辆轨迹预测的应用 Application of Spatial-Temporal Graph Attention Networks in Trajectory Prediction for Vehicles at Intersections 计算机科学, 2021, 48(6A): 334-341. https://doi.org/10.11896/jsjkx.200800066 |
| [11] | 杜少华, 万怀宇, 武志昊, 林友芳. 融合文本序列和图信息的海关商品HS编码分类 Customs Commodity HS Code Classification Integrating Text Sequence and Graph Information 计算机科学, 2021, 48(4): 97-103. https://doi.org/10.11896/jsjkx.200900053 |
| [12] | 刘志鑫, 张泽华, 张杰. 基于多层次多视角的图注意力Top-N推荐方法 Top-N Recommendation Method for Graph Attention Based on Multi-level and Multi-view 计算机科学, 2021, 48(4): 104-110. https://doi.org/10.11896/jsjkx.200800027 |
| [13] | 富坤, 赵晓梦, 付紫桐, 高金辉, 马浩然. 基于不完全信息的深度网络表示学习方法 Deep Network Representation Learning Method on Incomplete Information Networks 计算机科学, 2021, 48(12): 212-218. https://doi.org/10.11896/jsjkx.201000015 |
| [14] | 邢长征, 朱金侠, 孟祥福, 齐雪月, 朱尧, 张峰, 杨一鸣. 兴趣点推荐方法研究综述 Point-of-interest Recommendation:A Survey 计算机科学, 2021, 48(11A): 176-183. https://doi.org/10.11896/jsjkx.201100021 |
| [15] | 潘雨, 邹军华, 王帅辉, 胡谷雨, 潘志松. 基于网络表示学习的深度社团发现方法 Deep Community Detection Algorithm Based on Network Representation Learning 计算机科学, 2021, 48(11A): 198-203. https://doi.org/10.11896/jsjkx.210200113 |
|
||
首页