Multi-Source Knowledge-Based Hybrid Neural Framework for Time Series Representation Learning
This work addresses forecasting challenges in interconnected sensor networks for applications like risk minimization, representing an incremental improvement by integrating existing approaches.
The paper tackles the problem of accurately predicting complex dynamical systems using multivariate time series data by proposing a hybrid architecture that combines domain-specific knowledge and implicit relational structures, outperforming state-of-the-art forecasting methods on multiple benchmarks.
Accurately predicting the behavior of complex dynamical systems, characterized by high-dimensional multivariate time series(MTS) in interconnected sensor networks, is crucial for informed decision-making in various applications to minimize risk. While graph forecasting networks(GFNs) are ideal for forecasting MTS data that exhibit spatio-temporal dependencies, prior works rely solely on the domain-specific knowledge of time-series variables inter-relationships to model the nonlinear dynamics, neglecting inherent relational structural dependencies among the variables within the MTS data. In contrast, contemporary works infer relational structures from MTS data but neglect domain-specific knowledge. The proposed hybrid architecture addresses these limitations by combining both domain-specific knowledge and implicit knowledge of the relational structure underlying the MTS data using Knowledge-Based Compositional Generalization. The hybrid architecture shows promising results on multiple benchmark datasets, outperforming state-of-the-art forecasting methods. Additionally, the architecture models the time varying uncertainty of multi-horizon forecasts.