计算机科学 ›› 2020, Vol. 47 ›› Issue (3): 192-199.doi: 10.11896/jsjkx.190300137

• 人工智能 • 上一篇    下一篇

基于深度学习的多标签生成研究进展

刘晓玲,刘柏嵩,王洋洋,唐浩   

  1. (宁波大学信息科学与工程学院 浙江 宁波315211)
  • 收稿日期:2019-03-26 出版日期:2020-03-15 发布日期:2020-03-30
  • 通讯作者: 刘柏嵩(lbs@nbu.edu.cn)
  • 基金资助:
    国家社会科学基金(15FTQ002)

Research and Development of Multi-label Generation Based on Deep Learning

LIU Xiao-ling,LIU Bai-song,WANG Yang-yang,TANG Hao   

  1. (Faculty of Information Science and Technology, Ningbo University, Ningbo, Zhejiang 315211, China)
  • Received:2019-03-26 Online:2020-03-15 Published:2020-03-30
  • About author:LIU Xiao-ling, born in 1994,postgra-duate.Her main research interests include natural language processing and data mining. LIU Bai-song,born in 1971,Ph.D,researcher,Ph.D supervisor,is member of China Computer Federation.His main research interests include natural language processing,big data and artificial intelligence.
  • Supported by:
    This work was supported by the National Social Science Foundation of China (15FTQ002).

摘要: 大数据时代,数据呈现维度高、数据量大和增长快等特点。如何有效利用其中蕴含的有价值信息,以实现数据的智能化处理,已成为当前理论和应用的研究热点。针对现实普遍存在的多义性对象,数据多标签被提出并被广泛应用于数据智能化组织。近年来,深度学习在数据特征提取方面呈现出高速、高精度等优异性,使基于深度学习的多标签生成得到广泛关注。文中分五大类别总结了最新研究成果,并进一步从数据、关系类型、应用场景、适应性及实验性能方面对其进行对比和分析,最后探讨了多标签生成面临的挑战和未来的研究方向。

关键词: 深度学习, 多标签学习, 标签相关性, 神经网络

Abstract: In the era of big data,data show the characteristics of high dimension,large amount and rapid growth.Efficiently discovering knowledge from these data is a research focus.Multi-label has been proposed for ambiguous objects in reality,and is widely used in data intelligent processing.In recent years,Multi-label generation receives widespread attention due to the excellent performance of deep learning.The latest research results were summarized from five categories and were further compared and analyzed from the aspects of data,relationship types,application scene,adaptability and experimental performance.Finally,the challenges of multi-label generation were discussed,followed with the prospects for future work.

Key words: Deep learning, Multi-label learning, Label correlation, Neural networks

中图分类号: 

  • TP391
[1]ALAZAIDAH R,THABTAH F,AL-RADAIDEH Q.A Multi-label Classification Approach Based on Correlations Among Labels[J].International Journal of Advanced Computer Science and Applications,2015,6(2):52-59.
[2]CORANI G,SCANAGATTA M.Air Pollution Prediction via Multi-label Classification[J].Environmental Modelling & Software,2016,80(6):259-264.
[3]ZHANG M L,WU L.Lift:Multi-label learning with label-spe- cific features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(1):107-120.
[4]SONG Z,QIU Q.Learn to Classify and Count:A Unified Framework for Object Classification and Counting[C]∥Proceedings of the 2018 International Conference on Image and Graphics Processing.ACM,2018:110-114.
[5]HUANG C Q,YANG S M,PAN Y,et al.Object-location-aware hashing for multi-label image retrieval via automatic mask lear-ning[J].IEEE Transactions on Image Processing,2018,27(9):4490-4502.
[6]LI Z,LIAO B,LI Y,et al.Gene Function Prediction Based on Combining Gene Ontology Hierarchy with Multi-instance Multi-label Learning[J].Rsc Advances,2018,8(50):28503-28509.
[7]CAKIR E,HEITTOLA T,HUTTUNEN H,et al.Polyphonic sound event detection using multi label deep neural networks[C]∥International Joint Conference on Neural Networks.IEEE,2015:1-7.
[8]ZHANG C.Multi-label Text Categorization of Zhi Hu Title Based on Deep Learning[D].Beijing:Beijing Jiaotong University,2018.
[9]SUN J J,PEI L,JIANG T.Research on Semantic Annotation in Academic Literature[J].Journal of the China Society for Scientific and Technical Information,2018,37(11):1077-1086.
[10]ZHANG M L,ZHOU Z H.A review on multi-label learning algorithms[J].IEEE transactions on knowledge and data engineering,2014,26(8):1819-1837.
[11]ZHANG J J.Research on Key Problems of Multi-label Learning[D].Xi’an:Xidian University,2016.
[12]SPOLAÔR N,MONARD M C,TSOUMAKAS G,et al.A systematic review of multi-label feature selection and a new method based on label construction[J].Neurocomputing,2016180(C):3-15.
[13]WANG S B,LI Y F.Classifier Circle Method for Multi-Label Learning[J].Journal of Software,2015,26(11):2811-2819.
[14]PENG Y.Research on multi-label learning problems based on topic model[D].Nanjing:Nanjing University,2018.
[15]FU D,ZHOU B,HU J.Improving SVM based multi-label classification by using label relationship[C]∥2015 International Joint Conference on Neural Networks (IJCNN).IEEE,2015:1-6.
[16]YAN Y.Text Representation and Classification with Deep Learning[D].Beijing:University of Science & Technology Beijing,2016.
[17]LI S L,LIU R,LIU H.Multi-label Learning for Improved RBF Neural Networks[J].Computer Science,2015,42(4):316-320.
[18]ABDECHIRI M,FAEZ K.Efficacy of utilizing a hybrid algorithmic method in enhancing the functionality of multi-instance multi-label radial basis function neural networks[J].Applied Soft Computing,2015,34(C):788-798.
[19]ZHANG N,DING S,ZHANG J.Multi-Layer Elmrbf for Multi-label Learning[J].Applied Soft Computing,2016,43(C):535-545.
[20]LI G,NIU P,DUAN X,et al.Fast learning network:a novel artificial neural network with a fast learning speed[J].Neural Computing and Applications,2014,24(7/8):1683-1695.
[21]DANG D,XU X Z.Multi-label learning Model Based on Radial Basis Function Neural Network and Regularized Extreme Learning Machine[J].Pattern Recognition and Artificial Intelligence,2017,30(9):67-74.
[22]Y YEH C K,WU W C,KO W J,et al.Learning deep latent space for multi-label classification[C]∥Thirty-First AAAI Conference on Artificial Intelligence.AAAI,2017:2838-2844.
[23]NAM J,KIM J,MENCíA E L,et al.Large-scale multi-label text classification revisiting neural networks[C]∥Machine Learning and Knowledge Discovery in Databases-European Conference.Springer,2014:437-452.
[24]XIE P,SALAKHUTDINOV R,MOU L,et al.Deep determinantal point process for large-scale multi-label classification[C]∥Proceedings of the IEEE International Conference on Computer Vision.IEEE Computer Society,2017:473-482.
[25]KURATA G,XIANG B,ZHOU B.Improved Neural Network-based Multi-label Classification with Better Initialization Leveraging Label Co-occurrence[C]∥Proceedings of the 2016 Confe-rence of the North American Chapter of the Association for Computational Linguistics.ACL,2016:521-526.
[26]HÜLLERMEIER E,CHENG W.Superset Learning Based on Generalized Loss Minimization[C]∥Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Springer,2015:260-275.
[27]LIU J,CHANG W C,WU Y,et al.Deep learning for extreme multi-label text classification[C]∥Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2017:115-124.
[28]CHEN G,YE D,XING Z,et al.Ensemble application of convolutional and recurrent neural networks for multi-label text categorization[C]∥2017 International Joint Conference on Neural Networks.IEEE,2017:2377-2383.
[29]ZHAO B,LI X,LU X,et al.A CNN-RNN architecture for multi-label weather recognition[J].Neurocomputing,2018(12),322:47-57.
[30]YUAN Y,XUN G,MA F,et al.A novel channel-aware attention framework for multi-channel EEG seizure detection via multi-view deep learning[C]∥2018 IEEE EMBS International Conference on Biomedical & Health Informatics.IEEE,2018:206-209.
[31]SONG P,JING L P.Exploiting Label Relationships in Multi-Label Classification with Neural Networks[J].Journal of ComputerResearch and Development,2018,55(8):1751-1759.
[32]GENG X,XU N.Label distribution learning and label enhancement[J].Scientia Sinica Informationis,2018,48(5):521-530.
[33]GAO B B,XING C,XIE C W,et al.Deep label distribution learning with label ambiguity[J].IEEE Transactions on Image Processing,2017,26(6):2825-2838.
[34]LIU W,WEN Y,YU Z,et al.Large-Margin Softmax Loss for Convolutional Neural Networks [C]∥Proceedings of the 33nd International Conference on Machine Learning.JMLR,2016:507-516.
[35]DURAND T,THOME N,CORD M.Weldon:Weakly super- vised learning of deep convolutional neural networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2016:4743-4752.
[36]WU B,LYU S,GHANEM B.Constrained submodular minimization for missing labels and class imbalance in multi-label lear-ning[C]∥Thirtieth AAAI Conference on Artificial Intelligence.AAAI,2016:2229-2236.
[37]WU B,JIA F,LIU W,et al.Multi-label learning with missing labels using mixed dependency graphs[J].International Journal of Computer Vision,2018,126(8):875-896.
[38]WANG M,FU W,HAO S,et al.Scalable semi-supervised lear- ning by efficient anchor graph regu-larization[J].IEEE Transactions on Knowledge and Data Engineering,2016,28(7):1864-1877.
[39]JING L,YANG L,YU J,et al.Semi-supervised low-rank mapping learning for multi-label classification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2015:1483-1491.
[40]LIN G,LIAO K,SUN B,et al.Dynamic Graph Fusion Label Propagation for Semi-supervised Multi-modality Classification[J].Pattern Recognition,2017,68(8):14-23.
[41]WU F,WANG Z,ZHANG Z,et al.Weakly semi-supervised deep learning for multi-label image annotation[J].IEEETransa-ctions on Big Data,2015,1(3):109-122.
[42]PAPANIKOLAOU Y,TSOUMAKAS G,KATAK-IS I.Hierarchical partitioning of the output space in multi-label data[J].Data & Knowledge Engineering,2018,116(7):42-60.
[43]CHU H M,YEH C K,WANG Y C.Deep Generative Models for Weakly-Supervised Multi-Label Classification[C]∥Proceedings of the European Conference on Computer Vision (ECCV).Springer,2018:400-415.
[44]WEI Y,LIANG X,CHEN Y,et al.Stc:A simple to complex framework for weakly-supervised semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(11):2314-2320.
[45]LI Y,YANG J,SONG Y,et al.Learning from noisy labels with distillation[C]∥Proceedings of the IEEE International Confe-rence on Computer Vision.IEEE Computer Society,2017:1910-1918.
[46]ZHAO G,XU J,ZENG Q,et al.Driven Multi-label Music Style Classification by Exploiting Style Correlations[J].arXiv:1808.07604,2018.
[47]ZHU F,LI H,OUYANG W,et al.Learning spatial regularization with image-level supervisions for multi-label image classification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2017:5513-5522.
[48]VINYALS O,BENGIO S,KUDLUR M.Order matters:Se- quence to sequence for sets [J].arXiv:1511.06391,2015.
[49]CHEN S F,CHEN Y C,YEH C K,et al.Order-free rnn with visual attention for multi-label classification[C]∥Thirty-Se-cond AAAI Conference on Artificial Intelligence.AAAI,2018:6714-6721.
[50]WEI J,PHAM K,O′CONNOR B,et al.Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar:A Case Study on Machine Translation[C]∥Conference on Empirical Methods in Natural Language Processing.ACL,2018:298-305.
[51]HU X,LI G,XIA X,et al.Deep code comment generation[C]∥Proceedings of the 26th Conference on Program Comprehension.ACM,2018:200-210.
[52]FU Z,TAN X,PENG N,et al.Style transfer in text:Exploration and evaluation[C]∥Thirty-Second AAAI Conference on Artificial Intelligence.AAAI,2018:663-670.
[53]AKAMA R,INADA K,INOUE N,et al.Generating stylistically consistent dialog responses with transfer learning[C]∥Procee-dings of the Eighth International Joint Conference on Natural Language Processing.2017:408-412.
[54]YANG P,SUN X,LI W.SGM:sequence generation model for multi-label classification[C]∥Proceedings of the 27th International Conference on Computational Linguistics.2018:3915-3926.
[55]LIN J,SU Q,YANG P,et al.Semantic-Unit-Based Dilated Convolution for Multi-Label Text Classification[C]∥Proceedings of the 2018 Conference on Empirical Methods in Natural Language Procesing.ACL,2018:4554-4564.
[56]GEHRING J,AULI M,GRANGIER D,et al.Convolutional sequence to sequence learning[C]∥Proceedings of the 34th International Conference on Machine Learning-Volume 70.JMLR,2017:1243-1252.
[57]LI W,REN X,DAI D,et al.Sememe prediction:Learning semantic knowledge from unstructured textual wiki descriptions[J].arxiv:1808.05437,2018.
[58]HE D,XIA Y,QIN T,et al.Dual learning for machine translation[C]∥Advances in Neural Information Processing Systems.MIT Press,2016:820-828.
[59]BAHDANAU D,BRAKEL P,XU K,et al.An actor-critic algorithm for sequence prediction[J].arXiv:1607.07086,2016.
[60]YIN Q,ZHANG Y,ZHANG W,et al.Deep reinforcement learning for chinese zero pronoun resolution[C]∥Annual Mee-ting of the Association for Computational Linguistics.ACL,2018:569-578.
[61]YANG P,MA S,ZHANG Y,et al.A Deep Reinforced Sequence-to-Set Model for Multi-Label Text Classification[J].arXiv:1809.03118,2018.
[62]ZHAO L,ZHANG C,ZHANG X,et al.A Deep Reinforced Training Method for Location-Based Image Captioning[C]∥Pacific Rim International Conference on Artificial Intelligence.Springer,2018:878-890.
[63]HE S,XU C,GUO T,et al.Reinforced Multi-Label Image Classification by Exploring Curriculum [C]∥Thirty-Second AAAI Conference on Artificial Intelligence.AAAI,2018:3183-3190.
[64]CHEN T,WANG Z,LI G,et al.Recurrent attentional reinforcement learning for multi-label image recognition[C]∥Thirty-Second AAAI Conference on Artificial Intelligence.AAAI,2018:6730-6737.
[65]TSAI C P,LEE H Y.Adversarial Learning of Label Dependency:A Novel Framework for Multi-class Classification[J].arXiv:1811.04 689,2018.
[66]ZHOU T,LI Z,ZHANG C,et al.An Improved Convolutional Neural Network Model with Adversarial Net for Multi-label Image Classification[C]∥Pacific Rim International Conference on Artificial Intelligence.Springer,2018:38-46.
[67]MEN K,BOIMEL P,JANOPAUL NAYLOR J,et al.Cascaded atrous convolution and spatial pyramid pooling for more accurate tumor target segmentation for rectal cancer radiotherapy[J].Physics in Medicine & Biology,2018,63(18):185016.
[68]BEHPOUR S.Arc:Adversarial robust cuts for semi-supervised and multi-label classification[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2018:1905-1907.
[69]ZHOU Z H.Learn ware:on the future of machine learning [J].Frontiers of Computer Science,2016,10(4):589-590.
[70]JIANG S,XU Y,WANG T.Multi-Label Metric Transfer Lear- ning Jointly Considering Instance Space and Label Space Distribution Divergence[J].IEEE Access,2019,7:10362-10373.
[1] 余雪勇, 陈涛. 边缘计算场景中基于虚拟映射的隐私保护卸载算法[J]. 计算机科学, 2021, 48(1): 65-71.
[2] 单美静, 秦龙飞, 张会兵. L-YOLO:适用于车载边缘计算的实时交通标识检测模型[J]. 计算机科学, 2021, 48(1): 89-95.
[3] 何彦辉, 吴桂兴, 吴志强. 基于域适应的X光图像的目标检测[J]. 计算机科学, 2021, 48(1): 175-181.
[4] 李亚男, 胡宇佳, 甘伟, 朱敏. 基于深度学习的miRNA靶位点预测研究综述[J]. 计算机科学, 2021, 48(1): 209-216.
[5] 王瑞平, 贾真, 刘畅, 陈泽威, 李天瑞. 基于DeepFM的深度兴趣因子分解机网络[J]. 计算机科学, 2021, 48(1): 226-232.
[6] 于文家, 丁世飞. 基于自注意力机制的条件生成对抗网络[J]. 计算机科学, 2021, 48(1): 241-246.
[7] 仝鑫, 王斌君, 王润正, 潘孝勤. 面向自然语言处理的深度学习对抗样本综述[J]. 计算机科学, 2021, 48(1): 258-267.
[8] 张艳梅, 楼胤成. 基于深度神经网络的庞氏骗局合约检测方法[J]. 计算机科学, 2021, 48(1): 273-279.
[9] 丁钰, 魏浩, 潘志松, 刘鑫. 网络表示学习算法综述[J]. 计算机科学, 2020, 47(9): 52-59.
[10] 庄世杰, 於志勇, 郭文忠, 黄昉菀. 基于Zoneout的跨尺度循环神经网络及其在短期电力负荷预测中的应用[J]. 计算机科学, 2020, 47(9): 105-109.
[11] 何鑫, 许娟, 金莹莹. 行为关联网络:完整的变化行为建模[J]. 计算机科学, 2020, 47(9): 123-128.
[12] 张佳嘉, 张小洪. 多分支卷积神经网络肺结节分类方法及其可解释性[J]. 计算机科学, 2020, 47(9): 129-134.
[13] 叶亚男, 迟静, 于志平, 战玉丽, 张彩明. 基于改进CycleGan模型和区域分割的表情动画合成[J]. 计算机科学, 2020, 47(9): 142-149.
[14] 朱玲莹, 桑庆兵, 顾婷婷. 基于视差信息的无参考立体图像质量评价[J]. 计算机科学, 2020, 47(9): 150-156.
[15] 赵钦炎, 李宗民, 刘玉杰, 李华. 基于信息熵的级联Siamese网络目标跟踪[J]. 计算机科学, 2020, 47(9): 157-162.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 雷丽晖,王静. 可能性测度下的LTL模型检测并行化研究[J]. 计算机科学, 2018, 45(4): 71 -75 .
[2] 孙启,金燕,何琨,徐凌轩. 用于求解混合车辆路径问题的混合进化算法[J]. 计算机科学, 2018, 45(4): 76 -82 .
[3] 张佳男,肖鸣宇. 带权混合支配问题的近似算法研究[J]. 计算机科学, 2018, 45(4): 83 -88 .
[4] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[5] 史雯隽,武继刚,罗裕春. 针对移动云计算任务迁移的快速高效调度算法[J]. 计算机科学, 2018, 45(4): 94 -99 .
[6] 周燕萍,业巧林. 基于L1-范数距离的最小二乘对支持向量机[J]. 计算机科学, 2018, 45(4): 100 -105 .
[7] 刘博艺,唐湘滟,程杰仁. 基于多生长时期模板匹配的玉米螟识别方法[J]. 计算机科学, 2018, 45(4): 106 -111 .
[8] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[9] 崔琼,李建华,王宏,南明莉. 基于节点修复的网络化指挥信息系统弹性分析模型[J]. 计算机科学, 2018, 45(4): 117 -121 .
[10] 王振朝,侯欢欢,连蕊. 抑制CMT中乱序程度的路径优化方案[J]. 计算机科学, 2018, 45(4): 122 -125 .