A Collaborative Learning Framework to Tag Refinement for Points of Interest

Tags of a Point of Interest (POI) can facilitate location-based services from many aspects like location search and place recommendation. However, many POI tags are often incomplete or imprecise, which may lead to performance degradation of tag-dependent applications. In this paper, we study the POI tag refinement problem which aims to automatically fill in the missing tags as well as correct noisy tags for POIs. We propose a tri-adaptive collaborative learning framework to search for an optimal POI-tag score matrix. The framework integrates three components to collaboratively (i) model the similarity matching between POI and tag, (ii) recover the POI-tag pattern via matrix factorization and (iii) learn to infer the most possible tags by maximum likelihood estimation. We devise an adaptively joint training process to optimize the model and regularize each component simultaneously. And the final refinement results are the consensus of multiple views from different components. We also discuss how to utilize various data sources to construct features for tag refinement, including user profile data, query data on Baidu Maps and basic properties of POIs. Finally, we conduct extensive experiments to demonstrate the effectiveness of our framework. And we further present a case study of the deployment of our framework on Baidu Maps.

[1]  Qingming Huang,et al.  Location-Based Parallel Tag Completion for Geo-Tagged Social Image Retrieval , 2017, ACM Trans. Intell. Syst. Technol..

[2]  Guocong Song,et al.  Collaborative Learning for Deep Neural Networks , 2018, NeurIPS.

[3]  Hui Xiong,et al.  Hydra: A Personalized and Context-Aware Multi-Modal Transportation Recommendation System , 2019, KDD.

[4]  Dong Liu,et al.  Image retagging , 2010, ACM Multimedia.

[5]  John Krumm,et al.  Placer: semantic place labels from diary data , 2013, UbiComp.

[6]  Jian Li,et al.  Demand driven store site selection via multiple spatial-temporal data , 2016, SIGSPATIAL/GIS.

[7]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[8]  Jaegul Choo,et al.  Nonnegative Matrix Factorization for Interactive Topic Modeling and Document Clustering , 2014 .

[9]  Hui Xiong,et al.  Intent-Aware Audience Targeting for Ride-Hailing Service , 2018, ECML/PKDD.

[10]  Wei Wu,et al.  A “semi-lazy” approach to probabilistic path prediction in dynamic environments , 2013, KDD.

[11]  Yanchi Liu,et al.  Point-of-Interest Demand Modeling with Human Mobility Patterns , 2017, KDD.

[12]  Ming-Wei Chang,et al.  Placer++: Semantic place labels beyond the visit , 2015, 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[13]  Edward Y. Chang,et al.  Using one-class and two-class SVMs for multiclass image annotation , 2005, IEEE Transactions on Knowledge and Data Engineering.

[14]  Qian Zhang,et al.  A survey and analysis on automatic image annotation , 2018, Pattern Recognit..

[15]  Charu C. Aggarwal,et al.  Scaling up Link Prediction with Ensembles , 2016, WSDM.

[16]  Václav Hlavác,et al.  Sequential Coordinate-Wise Algorithm for the Non-negative Least Squares Problem , 2005, CAIP.

[17]  Xue Li,et al.  A Locality Sensitive Low-Rank Model for Image Tag Completion , 2016, IEEE Transactions on Multimedia.

[18]  Manfred Hauswirth,et al.  Semantic Tagging of Places Based on User Interest Profiles from Online Social Networks , 2013, ECIR.

[19]  Krzysztof Janowicz,et al.  On the semantic annotation of places in location-based social networks , 2011, KDD.

[20]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[21]  Krystyna K. Matusiak Towards user-centered indexing in digital image collections , 2006, OCLC Syst. Serv..

[22]  Qiang Yang,et al.  Feature engineering for semantic place prediction , 2013, Pervasive Mob. Comput..

[23]  Shazia Wasim Sadiq,et al.  A Spatial-Temporal Topic Model for the Semantic Annotation of POIs in LBSNs , 2016, ACM Trans. Intell. Syst. Technol..

[24]  Bernardo A. Huberman,et al.  Usage patterns of collaborative tagging systems , 2006, J. Inf. Sci..

[25]  Dong Liu,et al.  Image Retagging Using Collaborative Tag Propagation , 2011, IEEE Transactions on Multimedia.

[26]  Anthony K. H. Tung,et al.  Automatic Itinerary Planning for Traveling Services , 2014, IEEE Transactions on Knowledge and Data Engineering.

[27]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[28]  Jianmin Wang,et al.  Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Fuzhen Zhuang,et al.  Exploring the Urban Region-of-Interest through the Analysis of Online Map Search Queries , 2018, KDD.

[30]  Rong Jin,et al.  Image Tag Completion by Noisy Matrix Recovery , 2014, ECCV.

[31]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[32]  Yang Zhang,et al.  Semantic Annotation for Places in LBSN through Graph Embedding , 2017, CIKM.

[33]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[34]  Lei Wu,et al.  Tag Completion for Image Retrieval , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[35]  Bin Li,et al.  POISketch: Semantic Place Labeling over User Activity Streams , 2016, IJCAI.

[36]  Shuicheng Yan,et al.  Image tag refinement towards low-rank, content-tag prior and error sparsity , 2010, ACM Multimedia.

[37]  Hui Xiong,et al.  Joint Representation Learning for Multi-Modal Transportation Recommendation , 2019, AAAI.

[38]  David A. Forsyth,et al.  Matching Words and Pictures , 2003, J. Mach. Learn. Res..