时空嵌入式生成对抗网络的地点预测方法<sup>*</sup>

doi:10.16451/j.cnki.issn1003-6059.201801005

摘要
图/表
参考文献(0)
相关文章 (11)

全文: PDF (925 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

定位技术的广泛使用可以积累大量的用户轨迹信息,为挖掘用户的行为轨迹提供便利.地点预测任务是众多基于位置服务的基础,学者们更关注如何有效利用这些轨迹数据进行地点预测.已有的方法或关注对长期模式(数天或数月)的预测,或致力于实时轨迹预测.文中研究的问题基于上述两者之间,即对弱实时条件下(数分钟或数小时)用户下一步的访问行为进行预测.为此,提出时空嵌入式的生成对抗网络模型(ST-GAN),在序列生成对抗网络的基础上,提出时空嵌入式长短时记忆生成模型(ST-LSTM)和时空嵌入式卷积神经网络判别模型(ST-CNN).ST-LSTM利用时空信息引导LSTM训练门机制,缓解数据的稀疏性.ST-CNN利用时空信息增强判别真伪访问序列的能力.此外,ST-GAN的训练优化机制使模型可以生成更多逼近真实的数据以引导模型学习,从而得到更好的预测效果.最后在真实的轨迹数据集上的实验验证ST-GAN的有效性.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	孔德江
	汤斯亮
	吴飞

关键词 ：地点预测, 时空嵌入, 长短时记忆模型, 卷积神经网络, 生成对抗网络

Abstract：

The wide use of positioning technology makes the mining of the people movements easy and plenty of trajectory data are recorded. How to efficiently handle these data for location prediction is a popular research topic as it is fundamental to location-based services(LBS). The existing methods focus either on long time (days or months) visit prediction(i.e. point of interest recommendation) or on real time location prediction(i.e. trajectory prediction). In this paper, the location prediction problem in weak real time conditions is discussed to predict users′ movement in next minutes or hours. A spatial-temporal long-short term memory model(ST-LSTM) combining spatial-temporal influence into LSTM model naturally is proposed to mitigate the data sparse problem. Furthermore, following the idea of generative adversarial network(GAN) for seq2seq learning, the ST-GAN model is proposed, and it takes the proposed ST-LSTM as the generator and the proposed spatial-temporal convolutional neural network(ST-CNN) as the discriminator. The minimax game of ST-GAN can produce more real enough data to train a better prediction model. The proposed ST-GAN is evaluated on a real world trajectory dataset and the results demonstrate the effectiveness of the proposed model.

Key words： Location Prediction Spatial-Temporal Embedding Long-Short Term Memory Network Convolutional Neural Network Generative Adversarial Network

收稿日期: 2017-09-15

基金资助:

国家重点基础研究发展计划(973计划)(No.2015CB3523 02)、国家自然科学基金项目(No.U1611461)、浙江省重点研发计划(No.2015C01027)资助

作者简介: 孔德江,博士研究生,主要研究方向为深度学习、推荐系统.E-mail:kdjysss@gmail.com.汤斯亮,博士,副教授,主要研究方向为多媒体分析、文本挖掘、统计学习.E-mail:siliang@cs.zju.edu.cn.吴飞(通讯作者),博士,教授,主要研究方向为跨媒体检索、稀疏表达、机器学习.E-mail:wufei@cs.zju.edu.cn.

引用本文:

孔德江, 汤斯亮, 吴飞. 时空嵌入式生成对抗网络的地点预测方法^*[J]. 模式识别与人工智能, 2018, 31(1): 49-60. KONG Dejiang, TANG Siliang, WU Fei. Location Prediction via Generative Adversarial Network with #br# Spatial Temporal Embedding. , 2018, 31(1): 49-60.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.201801005 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2018/V31/I1/49

[1] SIMMONS R, BROWNING B, ZHANG Y L, et al. Learning to Predict Driver Route and Destination Intent // Proc of the IEEE Intelligent Transportation Systems Conference. Washington, USA: IEEE, 2006: 127-132.
[2] LIAO L, PATTERSON D J, FOX D, et al. Learning and Inferring Transportation Routines. Artificial Intelligence, 2007, 171(5): 311-331.
[3] LIN M, HSU W J. Brownian Bridge Model for High Resolution Location Predictions // Proc of the Pacific-Asia Conference on Know-ledge Discovery and Data Mining. Berlin, Germany: Springer, 2014: 210-221.
[4] MONREALE A, PINELLI F, TRASARTI R, et al. WhereNext: A Location Predictor on Trajectory Pattern Mining // Proc of the 15th ACM SIGKDD international Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2009: 637-646.
[5] MORZY M. Mining Frequent Trajectories of Moving Objects for Location Prediction // Proc of the International Workshop on Machine Learning and Data Mining in Pattern Recognition. Berlin, Germany: Springer, 2007: 667-680.
[6] XUE A Y, ZHANG R, ZHENG Y, et al. Destination Prediction by Sub-trajectory Synthesis and Privacy Protection against Such Prediction // Proc of the 29th IEEE International Conference on Data Engineering. Washington, USA: IEEE, 2013: 254-265.
[7] CHEN M, LIU Y, YU X H. Predicting Next Locations with Object Clustering and Trajectory Clustering // Proc of the Pacific-Asia Conference on Knowledge Discovery and Data Mining. Berlin, Germany: Springer, 2015: 344-356.
[8] TRSARTI R, GUIDOTTI R, MONREALE A, et al. MyWay: Location Prediction via Mobility Profiling. Information Systems, 2017, 64: 360-367.
[9] YE M, YIN P F, LEE W C, et al. Exploiting Geographical Influence for Collaborative Point-of-Interest Recommendation // Proc of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2011: 325-334.
[10] YUAN Q, CONG G, MA Z Y, et al. Time-Aware Point-of-Interest Recommendation // Proc of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2013: 363-372.
[11] CHEN X F, ZENG Y F, CONG G, et al. On Information Coverage for Location Category Based Point-of-Interest Recommendation // Proc of the 29th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 37-43.
[12] LIAN D F, ZHAO C, XIE X, et al. GeoMF: Joint Geographical Modeling and Matrix Factorization for Point-of-Interest Recommendation // Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: USA: ACM, 2014: 831-840.
[13] LI X T, CONG G, LI X L, et al. Rank-GeoFM: A Ranking Based Geographical Factorization Method for Point of Interest Recommendation // Proc of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2015: 433-442.
[14] LIAN D F, ZHENG V W, XIE X. Collaborative Filtering Meets Next Check-in Location Prediction // Proc of the 22nd International Conference on World Wide Web. New York, USA: ACM, 2013: 231-232.
[15] CHENG C, YANG H Q, LYU M R, et al. Where You Like to Go Next: Successive Point-of-Interest Recommendation // Proc of the 23rd International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2013: 2605-2611.
[16] LIU Q, WU S, WANG L, et al. Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts // Proc of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 194-200.
[17] YUAN N J, ZHENG Y, XIE X, et al. Discovering Urban Functional Zones Using Latent Activity Trajectories. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(3): 712-725.
[18] VACA C, QUERCIA D, BONCHI F, et al. Taxonomy-Based Discovery and Annotation of Functional Areas in the City // Proc of the 9th International AAAI Conference on Web and Social Media. Palo Alto, USA: AAAI Press, 2015: 445-453.
[19] FENG S S, LI X T, ZENG Y F, et al. Personalized Ranking Met-ric Embedding for Next New Poi Recommendation[C/OL]. [2017-10-23]. https://www.ijcai.org/Proceedings/15/Papers/293.pdf.
[20] HOCHREITER S, SCHMIDHUBER J. Long Short-Term Memory. Neural Computation, 1997, 9(8): 1735-1780.
[21] YU L T, ZHANG W N, WANG J, et al. SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient // Proc of the 31st AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2017: 2852-2858.
[22] YANG Z, CHEN W, WANG F, et al. Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets[C/OL]. [2017-10-23]. https://arxiv.org/pdf/1703.04887.pdf.
[23] LI J W, MONREO W, SHI T L, et al. Adversarial Learning for Neural Dialogue Generation[C/OL]. [2017-10-23]. https://arxiv.org/pdf/1701.06547.pdf.
[24] 张志军,刘弘.上下文感知的移动社交网络推荐算法研究.模式识别与人工智能, 2015, 28(5): 404-410.
(ZHANG Z J, LIU H. Research on Context-Awareness Mobile SNS Recommendation. Pattern Recognition and Artificial Intelligence, 2015, 28(5): 404-410.)
[25] RENDLE S, FREUDENTHALER C, SCHMIDT-THIEME L. Factorizing Personalized Markov Chains for Next-Basket Recommendation // Proc of the 19th International Conference on World Wide Web. New York, USA: ACM, 2010: 811-820.
[26] XIAO T J, XU Y C, YANG K Y, et al. The Application of Two-Level Attention Models in Deep Convolutional Neural Network for Fine-Grained Image Classification // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 842-850.
[27] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[28] KARPATHY A, TODERICI G, SHETTY S, et al. Large-Scale Video Classification with Convolutional Neural Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 1725-1732.
[29] LIM Y. Convolutional Neural Networks for Sentence Classification[C/OL]. [2017-10-23]. https://arxiv.org/pdf/1408.5882.pdf.
[30] LAI S W, XU L H, LIU K, et al. Recurrent Convolutional Neural Networks for Text Classification // Proc of the 29th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 2267-2273.
[31] 廖祥文,张丽瑶,宋志刚,等.基于卷积神经网络的中文微博观点分类.模式识别与人工智能, 2016, 29(12): 1075-1082.
(LIAO X W, ZHANG L Y, SONG Z G, et al. Chinese Microblog Sentiment Classification Based on Convolutional Neural Network. Pattern Recognition and Artificial Intelligence, 2016, 29(12): 1075-1082.)
[32] 张剑,屈丹,李真.基于词向量特征的循环神经网络语言模型.模式识别与人工智能, 2015, 28(4): 299-305.
(ZHANG J, QU D, LI Z. Recurrent Neural Network Language Model Based on Word Vector Features. Pattern Recognition and Artificial Intelligence, 2015, 28(4): 299-305.)
[33] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative Adversarial Nets[C/OL]. [2017-10-23]. https://arxiv.org/pdf/1406.2661v1.pdf.
[34] DENTO E, CHINTALA S, SZLAM A, et al. Deep Generative Image Models Using a Laplacian Pyramid of Adversarial Networks // Proc of the 28th International Conference on Neural Information Processing Systems. Cambridge, USA: The MIT Press, 2015: 1486-1494.
[35] 王坤峰,鲁越,王雨桐,等.平行图像:图像生成的一个新型理论框架.模式识别与人工智能, 2017, 30(7): 577-587.
(WANG K F, LU Y, WANG Y T, et al. Parallel Imaging: A New Theoretical Framework for Image Generation. Pattern Recognition and Artificial Intelligence, 2017, 30(7): 577-587.)
[36] WILLIAMS R J, ZIPSER D. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks. Neural Computation, 1989, 1(2): 270-280.
[37] BENGIO Y, SIMARD P, FRASCONI P. Learning Long-Term Dependencies with Gradient Descent Is Difficult. IEEE Transactions on Neural Networks, 1994, 5(2): 157-166.
[38] HOCHREITER S, BENGIO Y, FRASCONI P, et al. Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies[C/OL]. [2017-10-23]. http://www.bioinf.jku.at/publications/older/ch7.pdf.