Robust Multi-Modal Forecasting: Integrating Static and Dynamic Features
This work addresses the need for explainable models in critical applications like healthcare, but it is incremental as it extends an existing framework.
The paper tackles the problem of improving transparency and interpretability in time series forecasting by integrating exogenous time series features with static features, demonstrating predictive performance while maintaining interpretability and robustness on synthetic datasets.
Time series forecasting plays a crucial role in various applications, particularly in healthcare, where accurate predictions of future health trajectories can significantly impact clinical decision-making. Ensuring transparency and explainability of the models responsible for these tasks is essential for their adoption in critical settings. Recent work has explored a top-down approach to bi-level transparency, focusing on understanding trends and properties of predicted time series using static features. In this work, we extend this framework by incorporating exogenous time series features alongside static features in a structured manner, while maintaining cohesive interpretation. Our approach leverages the insights of trajectory comprehension to introduce an encoding mechanism for exogenous time series, where they are decomposed into meaningful trends and properties, enabling the extraction of interpretable patterns. Through experiments on several synthetic datasets, we demonstrate that our approach remains predictive while preserving interpretability and robustness. This work represents a step towards developing robust, and generalized time series forecasting models. The code is available at https://github.com/jeremy-qin/TIMEVIEW