计算机科学 ›› 2021, Vol. 48 ›› Issue (8): 66-71.doi: 10.11896/jsjkx.200900055
杨宏鑫, 宋宝燕, 刘婷婷, 杜岳峰, 李晓光
YANG Hong-xin, SONG Bao-yan, LIU Ting-ting, DU Yue-feng, LI Xiao-guang
摘要: 现代信号处理中,越来越多的领域都需要存储和分析规模大、维度高、结构复杂的数据。张量作为向量和矩阵的高阶推广,在保证原始数据内在关系的前提下,可以更为直观地表示大规模数据的结构性。张量填充作为张量分析的一个重要分支,目前已被广泛应用于协同过滤、图像恢复、数据挖掘等领域。张量填充指从被噪声污染或存在数据缺失的张量中恢复出原始张量的手段,文中着眼于当前张量填充技术中时间复杂度较高的缺点,提出了基于耦合随机投影的张量填充方法。该方法的核心包括两个部分:耦合张量分解以及随机投影矩阵。通过随机投影矩阵,文中将原始高维张量投影到低维空间内生成替代张量,同时在低维空间内实现张量填充,进而提高算法的执行效率。同时,所提算法还利用耦合张量分解将填充后的低维张量映射到高维空间,从而实现原始张量的重构。最后,通过实验分析了所提算法的有效性和高效性。
中图分类号:
[1]ZHANG Y.Improved Sample Image Inpainting Algorithm Based on Image Structure Tensor[J].Journal of Chongqing University of Technology(Natural Science),2020,34(3):145-151. [2]XIE Q,ZHANG Y,MENG D Y.Survey on Tensor SparsityMeasure[J].Journal of Chongqing University of Posts and Tele-communications(Natural Science Edition),2019,31(3):340-347. [3]RENNIE D M,SREBRO N.Fast Maximum Margin Matrix Factorization for Collaborative Prediction[C]//Proceedings of International Conference on Machine Learning.2005:713-719. [4]CANRAL R S,TORRE F D,COSTCIRA J P,et al.MatrixCompletion for Multi-Lable Image Classification[C]//Procee-dings of Neural Information Processing Systems.2011:120-128. [5]KOLDA T,BADER B.Tensor decompositions and applications[J].SIAM Review,2009,51 (3):455-500. [6]CHEN D B,YANG X M.Block-coded Video Deblocking Based on Low-rank Tensor Recovery[J].Computer Science,2016,43(9):280-283. [7]LIU J,YE J,et al.Tensor completion for estimating missing va-lues in visual data[C]// Proceedings of IEEE International Conference on Computer Vision.2009:2114-2121. [8]LIU J,MUSIALSKI P,WONKA P,et al.Tensor completion for estimating missing values in visual data[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35 (1):208-220. [9]GANDY S,RECHT B,YAMADA I.Tensor completion andlow-n-rank tensor recovery via convex optimization[J].Inverse Problems,2011,27(2):025010. [10]ACAR E,DUNLAVY D M,KOLDA T G,et al.Scalable tensor factorizations for incomplete data[J].Chemometrics and Intelligent Laboratory Systems,2011,106(1):41-56. [11]XU Y,HAO R,YIN W,et al.Parallel matrix factorization for low-rank tensor completion[J].Inverse Problems and Imaging,2015,9(2):601-624. [12]SILVA C D,HERRMANN F J.Optimization on the Hierarchical Tucker manifold-Applications to tensor completion[J].Li-near Algebra and Its Applications,2015,481:131-173. [13]BIGONI D,ENGSIG-KARUP A P,MARZOUK Y M.Spectral tensor-train decomposition[J].Mathematics,2014,38(4):2405-2439. [14]XU Z,YAN F,QI Y.Bayesian Nonparametric Models for Multiway Data Analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(2):475-487. [15]FENG Y L,SUN W J.A Matrix Completion method based on Fast Random Projection[J].Computer Applications and Software,2019(9):106-110. [16]ARRIAGA R I,RUTTER D,CAKMAK M,et al.Visual Categorization with Random Projection[J].Neural Computation,2015,27(10):2132-2147. [17]YOST D.The Johnson-Lindenstrauss space[J].Extracta Mathe-maticae,2007,12(2):185-192. |
[1] | 王营丽, 姜聪聪, 冯小年, 钱铁云. 时间感知的兴趣点推荐方法 Time Aware Point-of-interest Recommendation 计算机科学, 2021, 48(9): 43-49. https://doi.org/10.11896/jsjkx.210400130 |
[2] | 宋昱, 孙文赟. 改进非线性结构张量的含噪图像边缘检测 Edge Detection in Images Corrupted with Noise Based on Improved Nonlinear Structure Tensor 计算机科学, 2021, 48(6): 138-144. https://doi.org/10.11896/jsjkx.200600017 |
[3] | 巫勇, 刘永坚, 唐瑭, 王洪林, 郑建成. 基于鲁棒低秩张量恢复的高光谱图像去噪 Hyperspectral Image Denoising Based on Robust Low Rank Tensor Restoration 计算机科学, 2021, 48(11A): 303-307. https://doi.org/10.11896/jsjkx.210200103 |
[4] | 钟颖宇, 陈松灿. 高阶多视图离群点检测 High-order Multi-view Outlier Detection 计算机科学, 2020, 47(9): 99-104. https://doi.org/10.11896/jsjkx.200600170 |
[5] | 张德干, 范洪瑞, 龚倡乐, 高瑾馨, 张婷, 赵彭真, 陈晨. 一种基于张量的车辆交通数据缺失估计新方法 New Method of Data Missing Estimation for Vehicle Traffic Based on Tensor 计算机科学, 2020, 47(6A): 505-511. https://doi.org/10.11896/JsJkx.190700045 |
[6] | 林敏鸿, 蒙祖强. 基于注意力神经网络的多模态情感分析 Multimodal Sentiment Analysis Based on Attention Neural Network 计算机科学, 2020, 47(11A): 508-514. https://doi.org/10.11896/jsjkx.191100041 |
[7] | 杨洋, 邸一得, 刘俊晖, 易超, 周维. 基于张量分解的排序学习在个性化标签推荐中的研究 Study on Learning to Rank Based on Tensor Decomposition in Personalized Tag Recommendation 计算机科学, 2020, 47(11A): 515-519. https://doi.org/10.11896/jsjkx.191100181 |
[8] | 吴振宇, 李云雷, 吴凡. 基于Tucker分解的半监督支持张量机 Semi-supervised Support Tensor Based on Tucker Decomposition 计算机科学, 2019, 46(9): 195-200. https://doi.org/10.11896/j.issn.1002-137X.2019.09.028 |
[9] | 徐书艳, 韩立新, 徐国夏. 基于张量分解的域适应算法 Domain Adaptation Algorithm Based on Tensor Decomposition 计算机科学, 2019, 46(12): 89-94. https://doi.org/10.11896/jsjkx.190300095 |
[10] | 钱江,王凡,郭庆杰. 二元非张量积型连分式插值 Bivariate Non-tensor-product-typed Continued Fraction Interpolation 计算机科学, 2018, 45(3): 83-91. https://doi.org/10.11896/j.issn.1002-137X.2018.03.014 |
[11] | 武昱, 闫光辉, 王雅斐, 马青青, 刘宇轩. 结合GPU技术的并行CP张量分解算法 Parallel CP Tensor Decomposition Algorithm Combining with GPU Technology 计算机科学, 2018, 45(11): 298-303. https://doi.org/10.11896/j.issn.1002-137X.2018.11.048 |
[12] | 贾伟, 华庆一, 张敏军, 陈锐, 姬翔, 王博. 基于冲突度和协同过滤的移动用户界面模式推荐 Mobile User Interface Pattern Recommendation Based on Conflict Degree and Collaborative Filtering 计算机科学, 2018, 45(10): 202-206. https://doi.org/10.11896/j.issn.1002-137X.2018.10.037 |
[13] | 孙艳歌,王志海,黄丹. 基于时间的局部低秩张量分解的协同过滤推荐算法 Time-based Local Collaborative Filtering Recommendation Algorithm on Tensor Factorization 计算机科学, 2017, 44(7): 227-231. https://doi.org/10.11896/j.issn.1002-137X.2017.07.040 |
[14] | 陈代斌,杨晓梅. 基于低秩张量恢复的视频块效应处理 Block-coded Video Deblocking Based on Low-rank Tensor Recovery 计算机科学, 2016, 43(9): 280-283. https://doi.org/10.11896/j.issn.1002-137X.2016.09.056 |
[15] | 张浩,何杰,李慧宗. 基于改进鱼群算法与张量分解的社会化标签推荐模型 Social Tagging Recommendation Model Based on Improved Artificial Fish Swarm Algorithm and Tensor Decomposition 计算机科学, 2016, 43(12): 168-172. https://doi.org/10.11896/j.issn.1002-137X.2016.12.030 |
|