STRGCN: Capturing Asynchronous Spatio-Temporal Dependencies for Irregular Multivariate Time Series Forecasting
This addresses forecasting challenges in real-world applications like sensor networks, but it is incremental as it builds on existing graph-based methods for time series.
The paper tackled the problem of forecasting irregular multivariate time series with asynchronous measurements by introducing STRGCN, a model that avoids pre-alignment and captures spatio-temporal dependencies directly through a graph representation, achieving state-of-the-art accuracy on four public datasets.
Irregular multivariate time series (IMTS) are prevalent in real-world applications across many fields, where varying sensor frequencies and asynchronous measurements pose significant modeling challenges. Existing solutions often rely on a pre-alignment strategy to normalize data, which can distort intrinsic patterns and escalate computational and memory demands. Addressing these limitations, we introduce STRGCN, a Spatio-Temporal Relational Graph Convolutional Network that avoids pre-alignment and directly captures the complex interdependencies in IMTS by representing them as a fully connected graph. Each observation is represented as a node, allowing the model to effectively handle misaligned timestamps by mapping all inter-node relationships, thus faithfully preserving the asynchronous nature of the data. Moreover, we enhance this model with a hierarchical ``Sandwich'' structure that strategically aggregates nodes to optimize graph embeddings, reducing computational overhead while maintaining detailed local and global context. Extensive experiments on four public datasets demonstrate that STRGCN achieves state-of-the-art accuracy, competitive memory usage and training speed.