一种协同过滤式零次学习方法
作者:
作者简介:

杨博(1974-),男,博士,教授,博士生导师,CCF杰出会员,主要研究领域为知识发现与知识工程,网络分析理论与应用,推荐系统,多智能体系统.
张春旭(1996-),女,学士,主要研究领域为数据挖掘,网络表示学习.
张钰雪晴(1997-),女,硕士,主要研究领域为零次学习,深度学习.
黄晶(1975-),女,博士,副教授,博士生导师,CCF专业会员,主要研究领域为大规模网络数据挖掘与学习,智能大数据处理,复杂网络分析,深度学习,多Agent系统,数据驱动的智能传染病防控.
彭羿达(1996-),男,学士,主要研究领域为计算机视觉.

通讯作者:

黄晶,E-mail:huangjing@jlu.edu.cn

中图分类号:

TP183

基金项目:

国家自然科学基金(61876069,62172185);吉林省自然科学基金(20200201036JC);吉林省科技厅重点研发项目(20180201044GX,20180201067GX)


Collaborative Filtering Based Zero-Shot Learning
Author:
Fund Project:

National Natural Science Foundation of China (61876069, 62172185); Jilin Province Natural Science Foundation (20200201036JC); Jilin Province Key Scientific and Technological Research and Development Project (20180201044GX, 20180201067 GX)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [54]
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    深度学习算法在很多有监督学习任务上达到了令人满意的结果,但其依赖于大量标注样本,并且使用特定类别训练的分类器,只能对这些类别进行分类.零次学习希望计算机像人类一样,能够结合历史经验与知识进行推理,无需使用大量新类别样本训练,便可达到识别新类别的效果.发现了零次学习任务存在“冷启动”以及矩阵稀疏两个特点,这些特点在推荐任务中同样存在.受推荐任务启发,将零次图像分类任务建模为矩阵填充问题,借鉴推荐领域中协同过滤算法,将稀疏的样本标签矩阵视为非稀疏的视觉特征矩阵和类别特征矩阵的内积结果,进而实现对新类别样本的分类预测.此外,构建了基于类间语义关联的语义图结构,使用图神经网络进行已知类别和新类别之间的知识迁移,以较小代价为类别学得准确的语义特征.在3个经典零次学习数据集上分别进行传统零次学习和广义零次学习实验,实验结果表明:提出的协同过滤式零次学习方法能够有效提升分类精度,且训练代价较小.

    Abstract:

    Many deep learning algorithms have achieved satisfactory results on many supervised learning tasks, but they rely on a large number of labeled samples, and the classifiers trained with specific categories can only classify these categories. Zero-shot learning wishes that the computer can reason like a human, it uses historical knowledge to infer the characteristics of new objects and has the ability to recognize novel categories without lots of samples. It is found that there are sparse matrix and "cold-start" phenomena in zero-shot learning task, these phenomena are also in the recommendation tasks. Inspired by the recommendation tasks, the zero-shot classification task is modeled as a matrix completion problem, hoping to learn from the collaborative filtering algorithms in the recommendation field, which regards the sparse labeled matrix as the product of the visual feature matrix and semantic feature matrix, and then classifies the novel samples. In order to make the semantic representation of each category more accurate, a semantic graph structure is constructed based on the semantic relations between categories and a graph neural network is applied on it for information transferring between known and novel categories. Traditional zero-shot learning and generalized zero-shot learning experiments are performed on three classic zero-shot learning data sets. The experimental results show that the collaborative filtering based zero-shot learning method proposed in this study can effectively improve the classification accuracy, and the training cost is relatively small.

    参考文献
    [1] Krizhevsky A, Sutskever I, Hinton G. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012,25:1097-1105.
    [2] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 770-778.
    [3] Hinton G, Deng L, Yu D, Dahl GE, Mohamed A, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath TN, Kingsbury B. Deep neural networks for acoustic modeling in speech recognition:The shared views of four research groups. IEEE Signal processing Magazine, 2012,29(6):82-97.
    [4] Graves A, Mohamed A, Hinton G. Speech recognition with deep recurrent neural networks. In:Proc. of the IEEE Int'l Conf. on Acoustics, Speech and Signal Processing. 2013. 6645-6649.
    [5] Fagnant D, Kockelman K. Preparing a nation for autonomous vehicles:Opportunities, barriers and policy recommendations. Transportation Research Part A:Policy and Practice, 2015,77:167-181.
    [6] Yao Q, Tian Y. A model predictive controller with longitudinal speed compensation for autonomous vehicle path tracking. Applied Sciences, 2019,9(22):4739.
    [7] Xian Y, Schiele B, Akata Z. Zero-shot learning-the good, the bad and theugly. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 4582-4591.
    [8] Wang X, Ye Y, Gupta A. Zero-shot recognition via semantic embeddings and knowledge graphs. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 6857-6866.
    [9] Su X, Khoshgoftaar T. A survey of collaborative filtering techniques. In:Proc. of the Advances in Artificial Intelligence. 2009.
    [10] Koren Y, Bell R. Advances in Collaborative Filtering. Recommender Systems Handbook. 2015. 77-118.
    [11] Annadani Y, Biswas S. Preserving semantic relations for zero-shot learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 7603-7612.
    [12] Changpinyo S, Chao WL, Gong B, Sha F. Synthesized classifiers for zero-shot learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 5327-5336.
    [13] Kodirov E, Xiang T, Gong S. Semantic autoencoder for zero-shot learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2017. 3174-3183.
    [14] Fu Y, Hospedales T, Xiang T, Gong S. Transductive multi-view zero-shot learning. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2015,37(11):2332-2345.
    [15] Fu Z, Xiang T, Kodirov E, Gong S. Zero-shot learning on semantic class prototype graph. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2017,40(8):2009-2022.
    [16] Kodirov E, Xiang T, Fu Z, Gong S. Unsupervised domain adaptation for zero-shot learning. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2015. 2452-2460.
    [17] Chen L, Zhang H, Xiao J, Liu W, Chang S. Zero-shot visual recognition using semantics-preserving adversarial embedding networks. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 1043-1052.
    [18] Lampert CH, Nickisch H, Harmeling S. Attribute-based classification for zero-shot visual object categorization. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2013,36(3):453-465.
    [19] Li Y, Zhang J, Zhang J, Huang K. Discriminative learning of latent features for zero-shot recognition. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 7463-7471.
    [20] Radovanovic M, Nanopoulos A, Ivanovic M. Hubs in space:Popular nearestneighbors in high-dimensional data. Journal of Machine Learning Research, 2010,11(Sept.):2487-2531.
    [21] Wang X, Ye Y, Gupta A. Zero-shot recognition via semantic embeddings andknowledge graphs. In:Proc. of the IEEE Conf. on Computer Visionand Pattern Recognition. 2018. 6857-6866.
    [22] Zhang L, Xiang T, Gong S. Learning a deep embedding model for zero-shotlearning. In:Proc. of the IEEE Conf. on Computer Vision and Patternrecognition. 2017. 2021-2030.
    [23] Changpinyo S, Chao WL, Gong B, Sha F. Classifier and exemplar synthesis forzero-shot learning. Int'l Journal of Computer Vision, 2020,128(1):166-201.
    [24] Changpinyo S, Chao WL, Sha F. Predicting visual exemplars of unseen classesfor zero-shot learning. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2017. 3476-3485.
    [25] Tsai H, Huang L, Salakhutdinov R. Learning robust visual-semanticembeddings. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2017. 3571-3580.
    [26] Liu S, Long M, Wang J, Jordan M. Generalized zero-shot learning with deepcalibration network. In:Proc. of the Advances in Neural Information Processing Systems. 2018. 2005-2015.
    [27] Goldberg D, Nichols D, Oki B, Terry D. Using collaborative filtering to weave aninformation tapestry. Communications of the ACM, 1992,35(12):61-70.
    [28] Linden G, Smith B, York J. Amazon.com recommendations:Item-to-item collaborative filtering. IEEE Internet Computing, 2003, 7(1):76-80.
    [29] Pazzani MJ, Billsus D. Content-based recommendation systems. In:Proc. of the Adaptive Web. Berlin, Heidelberg:Springer, 2007. 325-341.
    [30] Deng AL, Zhu YY, Shi BL. A collaborative filtering recommendation algorithm based on item rating prediction. Ruan Jian Xue Bao/Journal of Software, 2003,14(9):1621-1628(in Chinese with English abstract). http://www.jos.org.cn/1000-9825/14/1621.htm
    [31] Ungar L, Foster D. Clustering methods for collaborative filtering. In:Proc. of the AAAI Workshop on Recommendation Systems, Vol.1. 1998. 114-129.
    [32] Vozalis M, Margaritis K. Using SVD and demographic data for the enhancementof generalized collaborative filtering. Information Sciences, 2007,177(15):3017-3037.
    [33] Kampffmeyer M, Chen Y, Liang X, Wang H, Zhang Y, Xing E. Rethinking knowledge graph propagation for zero-shot learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2019. 11487-11496.
    [34] Xiao J, Hays J, Ehinger K, Oliva A, Torralba A. Sun database:Large-scale scene recognition from abbey to zoo. In:Proc. of the 2010 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition. IEEE, 2010. 3485-3492.
    [35] Wah C, Branson S, Welinder P, Perona P, Belongie S. The caltech-ucsdbirds-200-2011 dataset. Technical Report, CNS-TR-2011-001, 2011.
    [36] Deng J, Dong W, Socher R, Li L, Li K, Li F. Imagenet:A large-scale hierarchical image database. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. IEEE, 2009. 248-255.
    [37] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 770-778.
    [38] Lampert CH, Nickisch H, Harmeling S. Learning to detect unseen object classes by between-class attribute transfer. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. IEEE, 2009. 951-958.
    [39] Frome A, Corrado G, Shlens J, Bengio S, Dean J, Mikolovet T. Devise:A deep visual-semantic embedding model. In:Proc. of the Advances in Neural Information Processing Systems. 2013.
    [40] Norouzi M, Mikolov T, Bengio S, Singer Y, Shlens J, Frome A, Corrado G, Dean J. Zero-shot learning by convex combination of semantic embeddings. arXivpreprint arXiv:1312.5650, 2013.
    [41] Socher R, Ganjoo M, Sridhar H, Bastani O, Manning C, Ng A. Zero shot learning through cross-modal transfer. In:Proc. of the Advances in Neural Information Processing Systems. 2014.
    [42] Akata Z, Perronnin F, Harchaoui Z, Schmid C. Label-embedding for image classification. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2015,38(7):1425-1438.
    [43] Akata Z, Reed S, Walter D, Lee H, Schiele B. Evaluation of output embeddings for fine-grained image classification. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2015. 2927-2936.
    [44] Romera-Paredes B, Torr P. An embarrassingly simple approach to zero-shot learning. In:Proc. of the Int'l Conf. on Machine Learning. PMLR, 2015. 2152-2161.
    [45] Zhang Z, Saligrama V. Zero-shot learning via semantic similarity embedding. In:Proc. of the IEEE Int'l Conf. on Computer Vision. 2015. 4166-4174.
    [46] Xian Y, Akata Z, Sharma G, Nguyen Q, Hein M, Schiele B. Latent embeddings for zero-shot classification. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2016. 69-77.
    [47] Zhang H, Koniusz P. Zero-shot kernel learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2018. 7670-7679.
    [48] Ding Z, Liu H. Marginalized latent semantic encoder for zero-shot learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2019. 6191-6199.
    [49] Paul A, Krishnan NC, Munjal P. Semantically aligned bias reducing zero shot learning. In:Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition. 2019. 7056-7065.
    [50] Yu Y, Ji Z, Fu Y, Guo J, Pang Y, Zhang Z. Stacked semantics-guided attention model for fine-grained zero-shot learning. In:Advances in Neural Information Processing Systems. 2018. 5995-6004.
    [51] Zhu Y, Xie J, Tang Z, Peng X, Elgammal A. Semantic-guided multi-attention localization for zero-shot learning. In:Advances in Neural Information Processing Systems. 2019.
    [52] Xie G, Liu L, Zhu F, Zhao F, Zhang Z, Yao Y, Qin J, Shao L. Region graph embedding network for zero-shot learning. In:Proc. of the European Conf. on Computer Vision. Cham:Springer-Verlag, 2020. 562-580.
    附中文参考文献:
    [30] 邓爱林,朱扬勇,施伯乐.基于项目评分预测的协同过滤推荐算法.软件学报,2003(9):1621-1628. http://www.jos.org.cn/1000-9825/14/1621.htm
    相似文献
    引证文献
引用本文

杨博,张钰雪晴,彭羿达,张春旭,黄晶.一种协同过滤式零次学习方法.软件学报,2021,32(9):2801-2815

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-11-12
  • 最后修改日期:2021-02-11
  • 在线发布日期: 2021-09-15
  • 出版日期: 2021-09-06
文章二维码
您是第19791963位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号