DynaSTy: A Framework for SpatioTemporal Node Attribute Prediction in Dynamic Graphs
This addresses a critical need for applications like financial trust networks, biological networks, and social systems, though it is incremental as it builds on existing spatiotemporal graph neural networks by accommodating dynamic graphs.
The paper tackles the problem of multistep forecasting of node-level attributes in dynamic graphs, where graphs vary over time, and demonstrates that their method consistently outperforms strong baselines on RMSE and MAE metrics.
Accurate multistep forecasting of node-level attributes on dynamic graphs is critical for applications ranging from financial trust networks to biological networks. Existing spatiotemporal graph neural networks typically assume a static adjacency matrix. In this work, we propose an end-to-end dynamic edge-biased spatiotemporal model that ingests a multi-dimensional timeseries of node attributes and a timeseries of adjacency matrices, to predict multiple future steps of node attributes. At each time step, our transformer-based model injects the given adjacency as an adaptable attention bias, allowing the model to focus on relevant neighbors as the graph evolves. We further deploy a masked node-time pretraining objective that primes the encoder to reconstruct missing features, and train with scheduled sampling and a horizon-weighted loss to mitigate compounding error over long horizons. Unlike prior work, our model accommodates dynamic graphs that vary across input samples, enabling forecasting in multi-system settings such as brain networks across different subjects, financial systems in different contexts, or evolving social systems. Empirical results demonstrate that our method consistently outperforms strong baselines on Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE).