Proceedings Article•
Personalized ranking metric embedding for next new POI recommendation
25 Jul 2015-pp 2069-2075
TL;DR: This paper proposes a personalized ranking metric embedding method (PRME) to model personalized check-in sequences and develops a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance.
Abstract: The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. In this paper, we study the next new POI recommendation problem in which new POIs with respect to users' current location are to be recommended. The challenge lies in the difficulty in precisely learning users' sequential information and personalizing the recommendation model. To this end, we resort to the Metric Embedding method for the recommendation, which avoids drawbacks of the Matrix Factorization technique. We propose a personalized ranking metric embedding method (PRME) to model personalized check-in sequences. We further develop a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance. Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the state-of-the-art next POI recommendation methods.
Citations
More filters
01 Nov 2018
TL;DR: In this article, a self-attention based sequential model (SASRec) is proposed, which uses an attention mechanism to identify which items are'relevant' from a user's action history, and use them to predict the next item.
Abstract: Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the 'context' of users' activities on the basis of actions they have performed recently. To capture such patterns, two approaches have proliferated: Markov Chains (MCs) and Recurrent Neural Networks (RNNs). Markov Chains assume that a user's next action can be predicted on the basis of just their last (or last few) actions, while RNNs in principle allow for longer-term semantics to be uncovered. Generally speaking, MC-based methods perform best in extremely sparse datasets, where model parsimony is critical, while RNNs perform better in denser datasets where higher model complexity is affordable. The goal of our work is to balance these two goals, by proposing a self-attention based sequential model (SASRec) that allows us to capture long-term semantics (like an RNN), but, using an attention mechanism, makes its predictions based on relatively few actions (like an MC). At each time step, SASRec seeks to identify which items are 'relevant' from a user's action history, and use them to predict the next item. Extensive empirical studies show that our method outperforms various state-of-the-art sequential models (including MC/CNN/RNN-based approaches) on both sparse and dense datasets. Moreover, the model is an order of magnitude more efficient than comparable CNN/RNN-based models. Visualizations on attention weights also show how our model adaptively handles datasets with various density, and uncovers meaningful patterns in activity sequences.
1,202 citations
Proceedings Article•
12 Feb 2016TL;DR: RNN is extended and a novel method called Spatial Temporal Recurrent Neural Networks (ST-RNN) is proposed, which can model local temporal and spatial contexts in each layer with time-specific transition matrices for different time intervals and distance-specific transitions for different geographical distances.
Abstract: Spatial and temporal contextual information plays a key role for analyzing user behaviors, and is helpful for predicting where he or she will go next. With the growing ability of collecting information, more and more temporal and spatial contextual information is collected in systems, and the location prediction problem becomes crucial and feasible. Some works have been proposed to address this problem, but they all have their limitations. Factorizing Personalized Markov Chain (FPMC) is constructed based on a strong independence assumption among different factors, which limits its performance. Tensor Factorization (TF) faces the cold start problem in predicting future actions. Recurrent Neural Networks (RNN) model shows promising performance comparing with PFMC and TF, but all these methods have problem in modeling continuous time interval and geographical distance. In this paper, we extend RNN and propose a novel method called Spatial Temporal Recurrent Neural Networks (ST-RNN). ST-RNN can model local temporal and spatial contexts in each layer with time-specific transition matrices for different time intervals and distance-specific transition matrices for different geographical distances. Experimental results show that the proposed ST-RNN model yields significant improvements over the competitive compared methods on two typical datasets, i.e., Global Terrorism Database (GTD) and Gowalla dataset.
687 citations
Cites background or methods from "Personalized ranking metric embeddi..."
...And PFMC improves the performance greatly comparing with TF. PFMC-LR and PRME achieve further improvement with via incorporating distance information....
[...]
...• PRME (Feng et al. 2015): It takes distance between destination location and recent vistaed ones into consideration for learning embeddings....
[...]
...And Personalized Ranking Metric Embedding (PRME) method (Feng et al. 2015) learns embeddings as well as calculating the distance between destination location and recent visited ones....
[...]
02 Feb 2018
TL;DR: A memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation is designed, which store and update users» historical records explicitly, which enhances the expressiveness of the model.
Abstract: User preferences are usually dynamic in real-world recommender systems, and a user»s historical behavior records may not be equally important when predicting his/her future interests. Existing recommendation algorithms -- including both shallow and deep approaches -- usually embed a user»s historical records into a single latent vector/representation, which may have lost the per item- or feature-level correlations between a user»s historical records and future interests. In this paper, we aim to express, store, and manipulate users» historical records in a more explicit, dynamic, and effective manner. To do so, we introduce the memory mechanism to recommender systems. Specifically, we design a memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation. By leveraging the external memory matrix in MANN, we store and update users» historical records explicitly, which enhances the expressiveness of the model. We further adapt our framework to both item- and feature-level versions, and design the corresponding memory reading/writing operations according to the nature of personalized recommendation scenarios. Compared with state-of-the-art methods that consider users» sequential behavior for recommendation, e.g., sequential recommenders with recurrent neural networks (RNN) or Markov chains, our method achieves significantly and consistently better performance on four real-world datasets. Moreover, experimental analyses show that our method is able to extract the intuitive patterns of how users» future actions are affected by previous behaviors.
425 citations
Additional excerpts
...Beyond e-commerce, sequential recommendation has also been applied to various application scenarios such as POI recommendation [3, 4], music recommendation [1, 8, 29], browsing recommendation [35], etc....
[...]
09 Aug 2015
TL;DR: A ranking based geographical factorization method, called Rank-GeoFM, for POI recommendation, which addresses the two challenges of scarcity of check-in data and context information, and outperforms the state-of-the-art methods significantly in terms of recommendation accuracy.
Abstract: With the rapid growth of location-based social networks, Point of Interest (POI) recommendation has become an important research problem. However, the scarcity of the check-in data, a type of implicit feedback data, poses a severe challenge for existing POI recommendation methods. Moreover, different types of context information about POIs are available and how to leverage them becomes another challenge. In this paper, we propose a ranking based geographical factorization method, called Rank-GeoFM, for POI recommendation, which addresses the two challenges. In the proposed model, we consider that the check-in frequency characterizes users' visiting preference and learn the factorization by ranking the POIs correctly. In our model, POIs both with and without check-ins will contribute to learning the ranking and thus the data sparsity problem can be alleviated. In addition, our model can easily incorporate different types of context information, such as the geographical influence and temporal influence. We propose a stochastic gradient descent based algorithm to learn the factorization. Experiments on publicly available datasets under both user-POI setting and user-time-POI setting have been conducted to test the effectiveness of the proposed method. Experimental results under both settings show that the proposed method outperforms the state-of-the-art methods significantly in terms of recommendation accuracy.
340 citations
Additional excerpts
...10, 8, 26], and currently-visited POI [4, 6]....
[...]
24 Oct 2016
TL;DR: A generic graph-based embedding model is proposed that jointly captures the sequential effect, geographical influence, temporal cyclic effect and semantic effect in a unified way by embedding the four corresponding relational graphs into a shared low dimensional space and develops a novel time-decay method to dynamically compute the user's latest preferences.
Abstract: With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LBSNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). However, the extreme sparsity of user-POI matrix and cold-start issue create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Moreover, location-based recommendation requires spatiotemporal context awareness and dynamic tracking of the user's latest preferences in a real-time manner. To address these challenges, we stand on recent advances in embedding learning techniques and propose a generic graph-based embedding model, called GE, in this paper. GE jointly captures the sequential effect, geographical influence, temporal cyclic effect and semantic effect in a unified way by embedding the four corresponding relational graphs (POI-POI, POI-Region, POI-Time and POI-Word)into a shared low dimensional space. Then, to support the real-time recommendation, we develop a novel time-decay method to dynamically compute the user's latest preferences based on the embedding of his/her checked-in POIs learnt in the latent space. We conduct extensive experiments to evaluate the performance of our model on two real large-scale datasets, and the experimental results show its superiority over other competitors, especially in recommending cold-start POIs. Besides, we study the contribution of each factor to improve location-based recommendation and find that both sequential effect and temporal cyclic effect play more important roles than geographical influence and semantic effect.
332 citations
Cites background from "Personalized ranking metric embeddi..."
...PRME proposed by Feng et al. [6] is also the typical one which exploits pair-wise ranking scheme....
[...]
...[6] is also the typical one which exploits pair-wise ranking scheme....
[...]
...However, JIM slightly outperforms PRME-G on Foursquare dataset while PRME-G exceeds JIM on Gowalla....
[...]
...However, our work is a graph-based method, which integrates various factors into a shared metric by different bipartite graphs while PRME embeds user preference and sequential patterns in two different metric respectively, and only considered sequential patterns of POIs and geographical influence....
[...]
...PRME [6] is a personalized ranking metric embedding algorithm that jointly models the sequential transition of POIs and user preferences....
[...]
References
More filters
TL;DR: Locally linear embedding (LLE) is introduced, an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs that learns the global structure of nonlinear manifolds.
Abstract: Many areas of science depend on exploratory data analysis and visualization. The need to analyze large amounts of multivariate data raises the fundamental problem of dimensionality reduction: how to discover compact representations of high-dimensional data. Here, we introduce locally linear embedding (LLE), an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs. Unlike clustering methods for local dimensionality reduction, LLE maps its inputs into a single global coordinate system of lower dimensionality, and its optimizations do not involve local minima. By exploiting the local symmetries of linear reconstructions, LLE is able to learn the global structure of nonlinear manifolds, such as those generated by images of faces or documents of text.
15,106 citations
Proceedings Article•
18 Jun 2009TL;DR: In this article, the authors proposed a generic optimization criterion BPR-Opt for personalized ranking that is the maximum posterior estimator derived from a Bayesian analysis of the problem, which is based on stochastic gradient descent with bootstrap sampling.
Abstract: Item recommendation is the task of predicting a personalized ranking on a set of items (e.g. websites, movies, products). In this paper, we investigate the most common scenario with implicit feedback (e.g. clicks, purchases). There are many methods for item recommendation from implicit feedback like matrix factorization (MF) or adaptive k-nearest-neighbor (kNN). Even though these methods are designed for the item prediction task of personalized ranking, none of them is directly optimized for ranking. In this paper we present a generic optimization criterion BPR-Opt for personalized ranking that is the maximum posterior estimator derived from a Bayesian analysis of the problem. We also provide a generic learning algorithm for optimizing models with respect to BPR-Opt. The learning method is based on stochastic gradient descent with bootstrap sampling. We show how to apply our method to two state-of-the-art recommender models: matrix factorization and adaptive kNN. Our experiments indicate that for the task of personalized ranking our optimization method outperforms the standard learning techniques for MF and kNN. The results show the importance of optimizing models for the right criterion.
3,429 citations
21 Aug 2011
TL;DR: A model of human mobility that combines periodic short range movements with travel due to the social network structure is developed and it is shown that this model reliably predicts the locations and dynamics of future human movement and gives an order of magnitude better performance.
Abstract: Even though human movement and mobility patterns have a high degree of freedom and variation, they also exhibit structural patterns due to geographic and social constraints. Using cell phone location data, as well as data from two online location-based social networks, we aim to understand what basic laws govern human motion and dynamics. We find that humans experience a combination of periodic movement that is geographically limited and seemingly random jumps correlated with their social networks. Short-ranged travel is periodic both spatially and temporally and not effected by the social network structure, while long-distance travel is more influenced by social network ties. We show that social relationships can explain about 10% to 30% of all human movement, while periodic behavior explains 50% to 70%. Based on our findings, we develop a model of human mobility that combines periodic short range movements with travel due to the social network structure. We show that our model reliably predicts the locations and dynamics of future human movement and gives an order of magnitude better performance than present models of human mobility.
2,922 citations
"Personalized ranking metric embeddi..." refers background in this paper
...For example, Gaussian Mixture distribution[Cho et al., 2011; Cheng et al., 2012] and power law distribution [Ye et al., 2011; Yuan et al., 2013] have been proposed to model the geographical influence....
[...]
...The first dataset is the FourSquare check-ins within Singapore [Yuan et al., 2013] while the second one is the Gowalla check-ins dataset within California and Nevada [Cho et al., 2011]....
[...]
..., 2013] while the second one is the Gowalla check-ins dataset within California and Nevada [Cho et al., 2011]....
[...]
...Importance of POI recommendation has attracted a significant amount of research interest on developing recommendation techniques [Cho et al., 2011; Ye et al., 2011; Cheng et al., 2012; Yuan et al., 2013; Lian et al., 2014; Li et al., 2015]....
[...]
...For example, Gaussian Mixture distribution[Cho et al., 2011; Cheng et al., 2012] and power law distribution [Ye et al....
[...]
26 Apr 2010
TL;DR: This paper introduces an adaption of the Bayesian Personalized Ranking (BPR) framework for sequential basket data and shows that the FPMC model outperforms both the common matrix factorization and the unpersonalized MC model both learned with and without factorization.
Abstract: Recommender systems are an important component of many websites. Two of the most popular approaches are based on matrix factorization (MF) and Markov chains (MC). MF methods learn the general taste of a user by factorizing the matrix over observed user-item preferences. On the other hand, MC methods model sequential behavior by learning a transition graph over items that is used to predict the next action based on the recent actions of a user. In this paper, we present a method bringing both approaches together. Our method is based on personalized transition graphs over underlying Markov chains. That means for each user an own transition matrix is learned - thus in total the method uses a transition cube. As the observations for estimating the transitions are usually very limited, our method factorizes the transition cube with a pairwise interaction model which is a special case of the Tucker Decomposition. We show that our factorized personalized MC (FPMC) model subsumes both a common Markov chain and the normal matrix factorization model. For learning the model parameters, we introduce an adaption of the Bayesian Personalized Ranking (BPR) framework for sequential basket data. Empirically, we show that our FPMC model outperforms both the common matrix factorization and the unpersonalized MC model both learned with and without factorization.
1,788 citations
Proceedings Article•
01 Jan 2002TL;DR: This probabilistic framework makes it easy to represent each object by a mixture of widely separated low-dimensional images, which allows ambiguous objects, like the document count vector for the word "bank", to have versions close to the images of both "river" and "finance" without forcing the image of outdoor concepts to be located close to those of corporate concepts.
Abstract: We describe a probabilistic approach to the task of placing objects, described by high-dimensional vectors or by pairwise dissimilarities, in a low-dimensional space in a way that preserves neighbor identities. A Gaussian is centered on each object in the high-dimensional space and the densities under this Gaussian (or the given dissimilarities) are used to define a probability distribution over all the potential neighbors of the object. The aim of the embedding is to approximate this distribution as well as possible when the same operation is performed on the low-dimensional "images" of the objects. A natural cost function is a sum of Kullback-Leibler divergences, one per object, which leads to a simple gradient for adjusting the positions of the low-dimensional images. Unlike other dimensionality reduction methods, this probabilistic framework makes it easy to represent each object by a mixture of widely separated low-dimensional images. This allows ambiguous objects, like the document count vector for the word "bank", to have versions close to the images of both "river" and "finance" without forcing the images of outdoor concepts to be located close to those of corporate concepts.
1,593 citations