<ul data-eligibleForWebStory="true"><li>Researchers have introduced GKNet, a graph-aware state space model for inference tasks with time series over graphs.</li><li>The model includes a graph-induced state equation driven by noise over graph edges and a graph-filtered observation model.</li><li>Parameters in both state and observation models are learned from partially observed data for prediction and imputation.</li><li>To enhance scalability, a deep learning architecture inspired by Kalman neural networks is employed for end-to-end learning and parameter tracking.</li></ul>

GKNet: Graph Kalman Filtering and Model Inference via Model-based Deep Learning

Discover more