Siamese learning based on graph differential equation for Next-POI recommendation

Next Point-of-Interest (POI) recommendation is highly challenging in its ill-posedness of data sparsity and elusive motives. Many models, including sequence-and graph-based, have been proposed to alleviate these problems. However, they still contain drawbacks: they either need a more accurate depiction of users' complex trajectories or novel perspectives on temporal-variant features in the discretized sequences of visits. To better cope with the two challenges, we proposed a novel time-continuous model, namely POIGDE. Our model explicitly exploits continuous variation of users' interests by solving a graph differential equation (GDE) on users' interaction behaviors. To maintain an invariant distribution while solving GDEs, we utilize a time-serial graph along with an interval-aware attention mechanism to learn the dynamics of interest transference. This novel update mechanism helps to track the original data distribution by confining the update process in a linear combination manner. Under this restriction, our model can obtain item representations for prediction, which share the same distribution as the actual POIs with which users interact. This practice also applies Siamese Learning in the POI recommendation to directly learn from the representation of ground-truth labels. By comparison with positive samples, the inferred probability of POIs being visited in the future can be obtained based on similarity (i.e., mean square error) between high-dimensional representations of the corresponding POIs. Our model outperforms state-of-the-art models on three real-world datasets by 0.16-23.44%, showing its potential and prospects in the POI recommendation domain.