Spatial-temporal Data Based Personalized Sequential POI Recommendation

With the development of Location-based Social Networks(LBSNs),sequential Point-of-Interest(POI)recommendation has become the pivotal part in people's daily life.Generally,it takes as input a user's historical POI interaction sequence,mines the sequential dependency,models the user's preference and recommends a list of POIs that the user might be interested in.The past flourishing years of sequential POI recommendation began with the introduction of Self-Attention Network(SAN),which quickly superseded CNN or RNN as the state-of-the-art backbone.To realize the fine-grained users' behavior patterns modeling,recent works utilize modified attention mechanisms or neural network layers to process spatial-temporal factors.However,due to the significant increase on either model's parameter scale or computational burden,we argue that these methods can be further improved.In this paper,we exploit two lightweight approaches,Time Aware Position Encoder(TAPE)and Interval Aware Attention Block(IAAB),to impel SAN by considering the spatial-temporal intervals among POIs separately,where requiring neither extra parameters nor high computational cost.On the one hand,TAPE,adjusting the positions in sequence based on the timestamps dynamically and generating positional representations with sinusoidal transformation,can enhance sequence representations to reflect both the absolute order and relative temporal proximity among all POIs.On the other hand,IAAB,point-wise adding the scaled spatial-temporal intervals to the attention map,can promote the attention mechanism attaching importance to the spatial relation among all POIs under the constraints of time conditions and providing more explainable recommendation.We integrate these two modules into SAN and propose a Spatial-Temporal Interval-Aware sequential POI recommender,namely STi SAN,as an end-to-end deployment.Experimental results based on three public LBSN datasets and one real-world city transportation dataset demonstrate STi SAN's superior performance(average 13.01%improvement against the strongest baseline),and the advantage is still maintained on different sparsity levels.Take a step further,we verify the effectiveness of TAPE and IAAB under our STi SAN.Moreover,we validate the extensibility and interpretability of TAPE and IAAB through metric evaluation and visualization separately.In final,we make a detailed comparison to explore the influence of different hyper-parameter settings on recommendation accuracy.