Graphical RNN Models
This addresses the need for flexible modeling of interacting entities in time series data, though it appears incremental as it builds on existing RNN capabilities.
The paper tackles the problem of learning from multiple interdependent time series by introducing a framework that models entities and their interactions over time, achieving gains in weather prediction over strong baselines.
Many time series are generated by a set of entities that interact with one another over time. This paper introduces a broad, flexible framework to learn from multiple inter-dependent time series generated by such entities. Our framework explicitly models the entities and their interactions through time. It achieves this by building on the capabilities of Recurrent Neural Networks, while also offering several ways to incorporate domain knowledge/constraints into the model architecture. The capabilities of our approach are showcased through an application to weather prediction, which shows gains over strong baselines.