Exploiting Individual Graph Structures to Enhance Ecological Momentary Assessment (EMA) Forecasting
This work addresses forecasting challenges in psychopathology for EMA data, which is incremental as it applies existing GNN methods to this domain-specific problem.
The research tackled forecasting Ecological Momentary Assessment (EMA) data by using Recurrent and Temporal Graph Neural Networks (GNNs) to incorporate graph structures of variable relationships, resulting in a reduction of Mean Squared Error (MSE) to 0.84 from a baseline LSTM model's 1.02.
In the evolving field of psychopathology, the accurate assessment and forecasting of data derived from Ecological Momentary Assessment (EMA) is crucial. EMA offers contextually-rich psychopathological measurements over time, that practically lead to Multivariate Time Series (MTS) data. Thus, many challenges arise in analysis from the temporal complexities inherent in emotional, behavioral, and contextual EMA data as well as their inter-dependencies. To address both of these aspects, this research investigates the performance of Recurrent and Temporal Graph Neural Networks (GNNs). Overall, GNNs, by incorporating additional information from graphs reflecting the inner relationships between the variables, notably enhance the results by decreasing the Mean Squared Error (MSE) to 0.84 compared to the baseline LSTM model at 1.02. Therefore, the effect of constructing graphs with different characteristics on GNN performance is also explored. Additionally, GNN-learned graphs, which are dynamically refined during the training process, were evaluated. Using such graphs showed a similarly good performance. Thus, graph learning proved also promising for other GNN methods, potentially refining the pre-defined graphs.