Trajectory-based social circle inference

Learning explicit and implicit patterns in human trajectories plays an important role in many Location-Based Social Networks (LBSNs) applications, such as trajectory classification (e.g., walking, driving, etc.), trajectory-user linking, friend recommendation, etc. A particular problem that has attracted much attention recently - and is the focus of our work - is the Trajectory-based Social Circle Inference (TSCI), aiming at inferring user social circles (mainly social friendship) based on motion trajectories and without any explicit social networked information. Existing approaches addressing TSCI lack satisfactory results due to the challenges related to data sparsity, accessibility and model efficiency. Motivated by the recent success of machine learning in trajectory mining, in this paper we formulate TSCI as a novel multi-label classification problem and develop a Recurrent Neural Network (RNN)-based framework called DeepTSCI to use human mobility patterns for inferring corresponding social circles. We propose three methods to learn the latent representations of trajectories, based on: (1) bidirectional Long Short-Term Memory (LSTM); (2) Autoencoder; and (3) Variational autoencoder. Experiments conducted on real-world datasets demonstrate that our proposed methods perform well and achieve significant improvement in terms of macro-R, macro-F1 and accuracy when compared to baselines.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Huachun Tan,et al.  Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering , 2016, IJCAI.

[3]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[4]  Zhi-Hua Zhou,et al.  Multi-instance multi-label learning , 2008, Artif. Intell..

[5]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[6]  Zhi-Hua Zhou,et al.  ML-KNN: A lazy learning approach to multi-label learning , 2007, Pattern Recognit..

[7]  James She,et al.  Collaborative Variational Autoencoder for Recommender Systems , 2017, KDD.

[8]  Zhi-Hua Zhou,et al.  Multi-label Learning , 2017, Encyclopedia of Machine Learning and Data Mining.

[9]  Daqing Zhang,et al.  NationTelescope: Monitoring and visualizing large-scale collective behavior in LBSNs , 2015, J. Netw. Comput. Appl..

[10]  Dino Pedreschi,et al.  Trajectory pattern mining , 2007, KDD '07.

[11]  Andreas Züfle,et al.  Spatio-temporal prediction of social connections , 2017, GeoRich '17.

[12]  Yu-Chiang Frank Wang,et al.  Learning Deep Latent Spaces for Multi-Label Classification , 2017, ArXiv.

[13]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[14]  Quoc V. Le,et al.  Semi-supervised Sequence Learning , 2015, NIPS.

[15]  Cheng-Te Li,et al.  Inferring social relationships from mobile sensor data , 2014, WWW '14 Companion.

[16]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[17]  Zoubin Ghahramani,et al.  A Theoretically Grounded Application of Dropout in Recurrent Neural Networks , 2015, NIPS.

[18]  Ji Feng,et al.  Deep MIML Network , 2017, AAAI.

[19]  Fernando Pérez-Cruz,et al.  Deep Learning for Multi-label Classification , 2014, ArXiv.

[20]  Nitesh V. Chawla,et al.  Inferring user demographics and social strategies in mobile social networks , 2014, KDD.

[21]  Pengpeng Zhao,et al.  Weak Labeled Multi-Label Active Learning for Image Classification , 2015, ACM Multimedia.

[22]  Cheng Soon Ong,et al.  Learning Points and Routes to Recommend Trajectories , 2016, CIKM.

[23]  Wang-Chien Lee,et al.  Mining geographic-temporal-semantic patterns in trajectories for location prediction , 2013, ACM Trans. Intell. Syst. Technol..

[24]  Hui Xiong,et al.  Learning geographical preferences for point-of-interest recommendation , 2013, KDD.

[25]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[26]  Iead Rezek,et al.  Inferring social network structure in ecological systems from spatio-temporal data streams , 2012, Journal of The Royal Society Interface.

[27]  Mohammad Al Hasan,et al.  Link prediction using supervised learning , 2006 .

[28]  Huimin Zhang,et al.  User Personalized Satisfaction Prediction via Multiple Instance Deep Learning , 2016, WWW.

[29]  Graham Neubig,et al.  Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction , 2017, ACL.

[30]  Hui Ding,et al.  Querying and mining of time series data: experimental comparison of representations and distance measures , 2008, Proc. VLDB Endow..

[31]  Guangyan Huang,et al.  DoSTra: Discovering Common Behaviors of Objects Using the Duration of Staying on Each Location of Trajectories , 2015, AAAI 2015.

[32]  Dino Pedreschi,et al.  Unveiling the complexity of human mobility by querying and mining massive trajectory data , 2011, The VLDB Journal.

[33]  Ying Tan,et al.  Variational Autoencoder for Semi-Supervised Text Classification , 2017, AAAI.

[34]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[35]  Wang-Chien Lee,et al.  PGT: Measuring Mobility Relationship Using Personal, Global and Temporal Factors , 2014, 2014 IEEE International Conference on Data Mining.

[36]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[37]  Geoff Holmes,et al.  Classifier chains for multi-label classification , 2009, Machine Learning.

[38]  Markus Schneider,et al.  Similarity measurement of moving object trajectories , 2012, IWGS '12.

[39]  Yi Fang,et al.  Variational Deep Semantic Hashing for Text Documents , 2017, SIGIR.

[40]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[41]  Zhiyuan Liu,et al.  A Neural Network Approach to Joint Modeling Social Networks and Mobile Trajectories , 2016, ArXiv.

[42]  Christopher Leckie,et al.  Personalized Tour Recommendation Based on User Interests and Points of Interest Visit Durations , 2015, IJCAI.

[43]  Xiangliang Zhang,et al.  Minimizing User Involvement for Learning Human Mobility Patterns from Location Traces , 2016, AAAI.

[44]  Ganesh Ramakrishnan,et al.  Scalable Optimization of Multivariate Performance Measures in Multi-instance Multi-label Learning , 2017, AAAI.

[45]  Jun Zhao,et al.  Recurrent Convolutional Neural Networks for Text Classification , 2015, AAAI.

[46]  Wang-Chien Lee,et al.  Mining user similarity from semantic trajectories , 2010, LBSN '10.

[47]  Xin Li,et al.  Active Learning with Multi-Label SVM Classification , 2013, IJCAI.

[48]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[49]  Qiang Gao,et al.  Identifying Human Mobility via Trajectory Embeddings , 2017, IJCAI.

[50]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[51]  Tieniu Tan,et al.  Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts , 2016, AAAI.