Learning Large-scale Location Embedding From Human Mobility Trajectories with Graphs
This provides a general-purpose embedding model for Geo-aware applications, addressing computational cost and data sparsity issues at large scales, though it is incremental as it builds on existing embedding and graph methods.
The paper tackles the problem of learning location embeddings from human mobility data at large scales like cities or countries, proposing GCN-L2V, a GCN-aided skip-gram model that uses flow and spatial graphs to capture relationships, and empirically shows it is effective in experiments and case studies.
An increasing amount of location-based service (LBS) data is being accumulated and helps to study urban dynamics and human mobility. GPS coordinates and other location indicators are normally low dimensional and only representing spatial proximity, thus difficult to be effectively utilized by machine learning models in Geo-aware applications. Existing location embedding methods are mostly tailored for specific problems that are taken place within areas of interest. When it comes to the scale of a city or even a country, existing approaches always suffer from extensive computational cost and significant data sparsity. Different from existing studies, we propose to learn representations through a GCN-aided skip-gram model named GCN-L2V by considering both spatial connection and human mobility. With a flow graph and a spatial graph, it embeds context information into vector representations. GCN-L2V is able to capture relationships among locations and provide a better notion of similarity in a spatial environment. Across quantitative experiments and case studies, we empirically demonstrate that representations learned by GCN-L2V are effective. As far as we know, this is the first study that provides a fine-grained location embedding at the city level using only LBS records. GCN-L2V is a general-purpose embedding model with high flexibility and can be applied in down-streaming Geo-aware applications.