lyhanburger / cuiyue Goto Github PK

12 classical researchs on POI recommendation are gathered with coresponding paper and code.
ref: Yiding Liu, Tuan-Anh Pham, Gao Cong, Quan Yuan: An Experimental Evaluation of Point-of-interest Recommendation in Location-based Social Networks. 1010 - 1021. http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/paper.pdf

1.Exploiting Geographical Influence for Collaborative Point-of-Interest Recommendation
PDF: http://www.cse.cuhk.edu.hk/irwin.king.new/_media/presentations/p325.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/USG.zip
data: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/data/Gowalla.zip

2.Fused Matrix Factorization with Geographical and Social Influence in Location-based Social Networks
PDF: http://www.cse.cuhk.edu.hk/lyu/_media/conference/cheng-aaai12.pdf?id=home&cache=cache
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/MGMPFM.zip
data: is the same as 1.

Points of my interest:
paper: Multi-center check-in behaviour
codes: sparse matrix computation using scipy
more details about csipy.sparce please refer to https://docs.scipy.org/doc/scipy/reference/sparse.html#module-scipy.sparse

3.Exploring temporal effects for location recommendation on location-based social networks
PDF: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.416.4425&rep=rep1&type=pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/LRT.zip
data: is the same as 1.

4.Personalized geo-social location recommendation a kernel density estimation approach
PDF: http://www.cs.cityu.edu.hk/~chiychow/papers/ACMGIS_2013a.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/iGSLR.zip
data: is the same as 1.

Points of my interest:
paper: a unified framework integrating user preference, social influence, the geographical influence of users, and the personalized geographical influence of locations
codes: a smart way of computing 'sum' with return value

10.Exploiting geographical, social and categorical correlations for point-of-interest recommendations
PDF: http://www.cs.cityu.edu.hk/~chiychow/papers/SIGIR_2015.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/GeoSoCa.zip
data: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/data/Yelp.zip

Points of my interest:
paper: variable-bandwidth KDE

----------------------------------------------------------华丽的分割线---------------------------------------------------------------- Long time no sign in (so long as to forgot password:) ). It is exciting to find this project got two stars! Thank you so much. These are the very first starts I've got. Also many thanks to Liu et al.! It is them who have done these great intensive evaluation works (especially codes) and I'm only a porter.
Besides continue updating 12 papers, I am going to follow up with state-of-art works on recommendation systems, which will be presented in the new archive named "RecSys 2018-" More detailed discussion is also documented there.
2019.3.12
----------------------------------------------------------华丽的分割线---------------------------------------------------------------

5.Location recommendation in location-based social networks using user check-in data
PDF: https://www.researchgate.net/profile/Manolis_Terrovitis/publication/260294299_Location_Recommendation_in_Location-based_Social_Networks_using_User_Check-in_Data/links/0f317530ac8b50c7bc000000.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/LFBCA.zip
data: is the same as 1.

6.Lore: Exploiting sequential influence for location recommendations
PDF: http://users.wpi.edu/~yli15/Includes/SIGSPATIAL2014_lore.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/LORE.zip
data: is the same as 1.

7. Exploiting geographical neighborhood characteristics for location recommendation
   PDF:http://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=4772&context=sis_research
   code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/IRenMF.zip
   data: is the same as 1.

8.Geomf: Joint geographical modeling and matrix factorization for point-of-interest recommendation
PDF: http://staff.ustc.edu.cn/~cheneh/paper_pdf/2014/Defu-Lian-KDD.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/GeoMF.zip
data: is the same as 1.

*9.Rank-geofm: A ranking based geographical factorization method for point of interest recommendation
PDF: https://www.researchgate.net/profile/Xutao_Li2/publication/278031194_Rank-GeoFM_A_Ranking_based_Geographical_Factorization_Method_for_Point_of_Interest_Recommendation/links/55d2c94e08ae0b8f3ef8e812.pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/RankGeoFM.zip
data: is the same as 1.

Points of my interest: The novelty of Rank-GeoFM lies in its definition of loss function. It considers the incompatibility between rankings and estimated scores of POIs. It worth mentioned that among all 12 models, Rank-GeoFM performs almost always the best in various metrics, according to Liu et al..

11.Geosoca: Exploiting geographical, social and categorical correlations for point-of-interest recommendations
PDF: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.703.9373&rep=rep1&type=pdf
code: http://spatialkeyword.sce.ntu.edu.sg/eval-vldb17/code/GeoSoCa.zip
data: is the same as 1.

12.Point-of-interest recommendations: Learning potential check-ins from friends
PDF: https://www.kdd.org/kdd2016/papers/files/rfp0448-liA.pdf
code: comming soon
data: is the same as 1.