Joint Geographical and Temporal Modeling Based on Matrix Factorization for Point-of-Interest Recommendation

Point-of-interest (POI) recommendation is a valuable service to help users discover attractive locations in location-based social networks (LBSNs). It focuses on capturing users’ movement patterns and location preferences by using massive historical check-in data. In the past decade, matrix factorization has become a mature and widely used technology in POI recommendation. However, the inner product of latent vectors adopted in matrix factorization methods does not satisfy the triangle inequality property, which may limit the expressiveness and lead to suboptimal solutions. Besides, the extreme sparsity of check-in data makes it challenging to capture users’ movement preferences accurately. In this paper, we propose a joint geosequential preference and distance metric factorization framework, called GeoSeDMF, for POI recommendation. First, we introduce a distance metric factorization method that is capable of learning users’ personalized preferences from a position and distance perspective in the metric space. Specifically, we convert the user-POI interaction matrix into a distance matrix and factorize it into user and POI dense embeddings. Additionally, we measure users’ personalized preference for the POI by using the Euclidean distance metric instead of the inner product. Then, we model the users’ geospatial preference by applying a geographic weight coefficient and model the users’ sequential preference by using the Euclidean distance of continuous check-in locations. Moreover, a pointwise loss strategy and AdaGrad algorithm are adopted to optimize the positions and relationships of users and POIs in a metric space. Finally, experimental results on three large-scale real-world datasets demonstrate the effectiveness and superiority of the proposed method.

Download Full-text

A Spatial-Temporal Probabilistic Matrix Factorization Model for Point-of-Interest Recommendation

Proceedings of the 2016 SIAM International Conference on Data Mining ◽

10.1137/1.9781611974348.14 ◽

2016 ◽

Cited By ~ 9

Author(s):

Huayu Li ◽

Richang Hong ◽

Zhiang Wu ◽

Yong Ge

Keyword(s):

Matrix Factorization ◽

Point Of Interest ◽

Factorization Model ◽

Probabilistic Matrix Factorization

Download Full-text

Context-aware probabilistic matrix factorization modeling for point-of-interest recommendation

Neurocomputing ◽

10.1016/j.neucom.2017.02.005 ◽

2017 ◽

Vol 241 ◽

pp. 38-55 ◽

Cited By ~ 45

Author(s):

Xingyi Ren ◽

Meina Song ◽

Haihong E ◽

Junde Song

Keyword(s):

Matrix Factorization ◽

Context Aware ◽

Point Of Interest ◽

Probabilistic Matrix Factorization

Download Full-text

An interpretable framework for investigating the neighborhood effect in POI recommendation

PLoS ONE ◽

10.1371/journal.pone.0255685 ◽

2021 ◽

Vol 16 (8) ◽

pp. e0255685

Author(s):

Guangchao Yuan ◽

Munindar P. Singh ◽

Pradeep K. Murukannaiah

Keyword(s):

Deep Learning ◽

Matrix Factorization ◽

State Of The Art ◽

Experimental Results ◽

Neighborhood Effect ◽

Data Set ◽

Point Of Interest ◽

Poi Recommendation ◽

Geographical Characteristics

Geographical characteristics have been proven to be effective in improving the quality of point-of-interest (POI) recommendation. However, existing works on POI recommendation focus on cost (time or money) of travel for a user. An important geographical aspect that has not been studied adequately is the neighborhood effect, which captures a user’s POI visiting behavior based on the user’s preference not only to a POI, but also to the POI’s neighborhood. To provide an interpretable framework to fully study the neighborhood effect, first, we develop different sets of insightful features, representing different aspects of neighborhood effect. We employ a Yelp data set to evaluate how different aspects of the neighborhood effect affect a user’s POI visiting behavior. Second, we propose a deep learning–based recommendation framework that exploits the neighborhood effect. Experimental results show that our approach is more effective than two state-of-the-art matrix factorization–based POI recommendation techniques.

Download Full-text

Periodic and Successive Point-of-interest Recommendation under Dual Social Group Influences with Matrix Factorization

Revista de la Facultad de Ingeniería ◽

10.21311/002.31.3.22 ◽

2016 ◽

Keyword(s):

Matrix Factorization ◽

Social Group ◽

Point Of Interest ◽

Successive Point

Download Full-text

Geo-Pairwise Ranking Matrix Factorization Model for Point-of-Interest Recommendation

Neural Information Processing - Lecture Notes in Computer Science ◽

10.1007/978-3-319-70139-4_37 ◽

2017 ◽

pp. 368-377 ◽

Cited By ~ 4

Author(s):

Shenglin Zhao ◽

Irwin King ◽

Michael R. Lyu

Keyword(s):

Matrix Factorization ◽

Point Of Interest ◽

Factorization Model

Download Full-text

The Advantages of Cryotechniques: Application To Bioluminescent Cells

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s042482010018118x ◽

1990 ◽

Vol 48 (1) ◽

pp. 486-487

Author(s):

Gisèle Nicolas ◽

Jean-Marie Bassot ◽

Marie-Thérèse Nicolas

Keyword(s):

Endoplasmic Reticulum ◽

Striated Muscle ◽

Light Emission ◽

Stable State ◽

Freeze Substitution ◽

Initial Step ◽

Point Of Interest ◽

Cell Components ◽

Excellent Preservation ◽

External Water

The use of fast-freeze fixation (FFF) followed by freeze-substitution (FS) brings substantial advantages which are due to the extreme rapidity of this fixation compared to the conventional one. The initial step, FFF, physically immobilizes most molecules and therefore arrests the biological reactions in a matter of milliseconds. The second step, FS, slowly removes the water content still in solid state and, at the same time, chemically fixes the other cell components in absence of external water. This procedure results in an excellent preservation of the ultrastructure, avoids osmotic artifacts,maintains in situ most soluble substances and keeps up a number of cell activities including antigenicities. Another point of interest is that the rapidity of the initial immobilization enables the capture of unstable structures which, otherwise, would slip towards a more stable state. When combined with electrophysiology, this technique arrests the ultrastructural modifications at a well defined state, allowing a precise timing of the events.We studied the epithelium of the elytra of the scale-worm, Harmothoe lunulata which has excitable, conductible and bioluminescent properties. The intracellular sites of the light emission are paracrystals of endoplasmic reticulum (PER), named photosomes (Fig.1). They are able to flash only when they are coupled with plasma membrane infoldings by dyadic or triadic junctions (Fig.2) basically similar to those of the striated muscle fibers. We have studied them before, during and after stimulation. FFF-FS showed that these complexes are labile structures able to diffentiate and dedifferentiate within milliseconds. Moreover, a transient network of endoplasmic reticulum was captured which we have named intermediate endoplasmic reticulum (IER) surrounding the PER (Fig.1). Numerous gap junctions are found in the membranous infoldings of the junctional complexes (Fig.3). When cryofractured, they cleave unusually (Fig.4-5). It is tempting to suggest that they play an important role in the conduction of the excitation.

Download Full-text