梁吉業;高嘉偉;常瑜;

• 1:山西大學計算智能與中文信息處理教育部重點實驗室
• 2:山西大學計算機與信息技術學院

摘要(Abstract)：

半監督學習問題廣泛存在于現實世界中,已經成為目前機器學習和模式識別領域中的一個研究熱點.文章綜述了半監督學習問題的基本思想、研究現狀、常用算法及其一些應用領域,分析了目前存在的主要困難,并指出需進一步研究的幾個問題.

關鍵詞(KeyWords)： 半監督學習;標簽;協同訓練;算法

Abstract:

Keywords:

基金項目(Foundation): 國家863計劃項目(2007AA01Z165);; 國家自然科學基金(60773133;70971080);; 山西省自然科學基金(2008011038)

作者(Author): 梁吉業;高嘉偉;常瑜;

Email:

DOI:

參考文獻(References)：

• [1]ZHU XJ.Semi-supervised Learning Literature Survey[R].Madison:University of Wisconsin,2008.
• [2]周志華.半監督學習中的協同訓練算法[M]//周志華,王玨.機器學習及其應用.北京:清華大學出版社,2007:259-275.
• [3]蘇金樹,張博鐸,徐昕.基于機器學習的文本分類技術研究進展[J].軟件學報,2006,17(9):1848-1859.
• [4]NIGAM K,MCCALLUM A K,THRUN S,MITCHELL T.Text Classification from Labeled and Unlabeled Documents using EM[J].Machine Learning,2000,39:103-134.
• [5]ZHOUZ H,CHEN KJ,YUANJ.Exploiting Unlabeled Data in Content-Based I mage Retrieval[C]//Proceedings ofthe15th European Conference on Machine Learning,Pisa,Italy,2004:525-536.
• [6]ZHOU Z H,CHEN K J,DAI H B.Enhancing Relevance Feedback in I mage Retrieval using Unlabeled Data[J].ACMTransactions on Information Systems,2006,24(2):219-244.
• [7]TSUDA K,RATSCH G.I mage Reconstruction by Linear Programming[J].IEEE Transactions on Image Processing,2005,14(6):737-744.
• [8]SONG Y Q,ZHANG C S,LEE J G,et al.Semi-supervised Discri minative Classification with Application to Tumorous Tissues Segmentation of MRLBrain I mages[J].Pattern Analysis&Applications,2009,12:99-115.
• [9]TANGJ,HUA X S,QI GJ,et al.Structure-Sensitive Manifold Ranking for Video Concept Detection[C]//Proceedings of the15th International Conference on Multi media,Augsburg,Germany,2007:852-861.
• [10]YAN R,NAPHADE M R.Semi-supervised Cross Feature Learning for Semantic Concept Detection in Videos[C]//Proceedings of the IEEE Computer Society International Conference on Computer Vision and Pattern Recognition,San Diego,USA,2005,1:657-663.
• [11]HE J R,LI MJ,ZHANG HJ,et al.Manifold-Ranking Based I mage Retrieval[C]//Proceedings of the12th Annual ACMInternational Conference on Multi media,New York,USA,2004:9-16.
• [12]FENG W,XIE L,ZENGJ,LI UZ Q.Audio-visual Human Recognition using Semi-supervised Spectral Learning and Hid-den Markov Models[J].Journal of Visual Languages and Computing,2009,20:188-195.
• [13]SHAHSHAHANI B,LANDGREBE D.The Effect of Unlabeled Samples in Reducing the Small Sample Size Problemand Mitigating the Hughes Phenomenon[J].IEEE Transactions on Geoscience and Remote Sensing,1994,32(5):1087-1095.
• [14]ZHOU D Y,BOUSQUET O,LAL T N,et al.Learning with Local and Global Consistency[M]//THRUN S,SAUL L K,SCHOLKOPF B.Advances in Neural Information Processing System16.Cambridge:The MIT Press,2004:321-328.
• [15]CHAPELLE O,ZIEN A.Semi-supervised Classification by Low Density Separation[C]//Proceedings ofthe10thInter-national Workshop on Artificial Intelligence and Statistics,Barbados,2005:57-64.
• [16]BLUM A,CHAWLA S.Learning from Labeled and Unlabeled Data using Graph Mincuts[C]//Proceedings ofthe18th International Conference on Machine Learning,Williamstown,USA,2001:19-26.
• [17]HOU D Y,SCHOLKOPF B,HOFMANN T.Semi-supervised Learning on Directed Graphs[J].Advancesin Neural In-formation Processing System,2005,17:1633-1640.
• [18]KULIS B,BASU S,DHILLONI,MOONEY R.Semi-supervised Graph Clustering:A Kernel Approach[J].Machine Learning,2009,74:1-22.
• [19]BLUM A,MITCHELL T.Combining Labeled and Unlabeled Data with Co-Training[C]//Proceedings of the11th An-nual Conference on Computational Learning Theory,Madison,USA,1998:92-100.
• [20]GOLDMAN.S,ZHOU Y.Enhancing Supervised Learning with Unlabeled Data[C]//Proceedings of17th International Conference on Machine Learning,San Francisco,Canada,2000:327-334.
• [21]ZHOU Z H,LI M.Tri-Training:Exploiting Unlabeled Data using Three Classifiers[J].IEEE Transactions on Knowl-edge and Data Engineering,2005,17(11):1529-1542.
• [22]鄧超,郭茂祖.基于Tri-Training和數據剪輯的半監督聚類算法[J].軟件學報,2008,19(3):663-673.
• [23]HE H T,LUO X N,MAF T,et al.Network Traffic Classification Based on Ensemble Learning and Co-training[J].Sci-ence in China Series F:Information Sciences,2009,52(2):338-346.
• [24]ZHOU Z H,LI M.I mprove Computer-aided Diagnosis with Machine Learning Techniques using Undiagnosed Samples[J].IEEE Transactions on Systems,Man and Cybernetics-PartA:Systems and Humans,2007,37(6):1088-1098.
• [25]ZHOU Z H,ZHAN D C,YANG Q.Semi-supervised Learning with Very Few Labeled Training Examples[C]//Pro-ceedings of the22nd AAAI Conference on Artificial Intelligence,Vancouver,Canada,2007:675-680.
• [26]GRANDVALET Y,BENGIO Y.Semi-supervised Learning by Entropy Mini mization[M]//SAUL L K,WEISS Y,BOT-TOU L.Advances in Neural Information Processing System17.Cambridge:The MIT Press,2005:529-536.
• [27]梁吉業,錢宇華.信息系統中的信息粒與熵理論[J].中國科學(E輯),2008,38(12):2048-2065.
• [28]梁吉業,李德玉.信息系統中的不確定性與知識獲取[M].北京:科學出版社,2005:37-42.
• [29]肖宇,于劍.基于近鄰傳播算法的半監督聚類[J].軟件學報,2008,19(11):2803-2813.
• [30]尹學松,胡恩良,陳松燦.基于成對約束的判別型半監督聚類分析[J].軟件學報,2008,19(11):2791-2802.
• [31]XIA Y.A Global Opti mization Method for Semi-supervised Clustering[J].Data Mining and Knowledge Discovery,2009,18:214-256.
• [32]門昌騫,王文劍.一種基于多學習器標記的半監督SVM學習方法[J].廣西師范大學學報:自然科學版,2008,26(1):186-189.
• [33]JOACHI MS T.Transductive Inference for Text Classification using Support Vector Machines[C]//Proceedings of the16th International Conference on Machine Learning,Bled,Slovenia,1999:200-209.
• [34]ZHOU Z H,LI M.Semi-supervised Regression with Co-training[C]//Proceedings ofthe19thInternational Joint Con-ference on Artificial Intelligence,Edinburgh,Scotland,2005:908-913.
• [35]BREFELD U,GAERTNER T,SCHEFFER T,WROBEL S.Efficient Co-regularized Least Squares Regression[C]//Proceedings of the23rdInternational Conference on Machine Learning,Pittsburgh,USA,2006:137-144.
• [36]楊劍,王玨,鐘寧.流形上的Laplacian半監督回歸[J].計算機研究與發展,2007,44(7):1121-1127.
• [37]LI U B,LEE WS,YU P S,LI X L.Partially Supervised Classification of Text Documents[C]//Proceedings of19thIn-ternational Conference on Machine Learning,Sydney,Australia,2002:387-394.
• [38]鄭海清,林琛,牛軍鈺.一種基于緊密度的半監督文本分類方法[J].中文信息學報,2007,21(3):54-60.
• [39]鄭聲恩,葉少珍.一種基于內容圖像檢索的半監督和主動學習算法[J].計算機工程與應用,2006:81-83,87.
• [40]WU Y,TIAN Q,HUANG TS.Discri minant-EMAlgorithm with Applicationto I mage Retrieval[C]//IEEEConference on Computer Vision and Pattern Recognition,Hilton Head Island,USA,2000,1:222-227.
• [41]SONG Y,HUA X S,DAI L R,WANG M.Semi-Automatic Video Annotation Based on Active Learning with Multiple Complementary Predictors[C]//Proceedings of the7th ACM SIGMMInternational Workshop on Multi media Infor-mation Retrieval,Hilton,Singapore,2005:97-104.
• [42]李和平,胡占義,吳毅紅,吳福朝.基于半監督學習的行為建模與異常檢測[J].軟件學報,2007,18(3):527-537.

文章評論(Comment)：