We address the problem of learning over multiple inter-dependent temporal sequences where dependencies are modeled by a graph. We propose a model that is able to simultaneously fill in missing values and predict future ones. This approach is based on representation learning techniques, where temporal data are represented in a latent vector space. Information completion (missing values) and prediction are then performed on this latent representation. In particular, the model allows us to perform both tasks using a unique formalism, whereas most often they are addressed separately using different methods. The model has been tested for a concrete application: cartraffic forecasting where each time series characterizes a particular road and where the graph structure corresponds to the road map of the city.
展开▼
