Context Neural Networks: A Scalable Multivariate Model for Time Series Forecasting
This work provides a scalable solution for time series forecasting in domains with complex interdependencies, though it is incremental as it builds on existing global and multivariate models.
The paper tackles the problem of forecasting interdependent time series by introducing Context Neural Networks, which efficiently incorporate real-time contextual information from neighboring series with linear complexity, addressing the scalability issues of existing multivariate models.
Real-world time series often exhibit complex interdependencies that cannot be captured in isolation. Global models that model past data from multiple related time series globally while producing series-specific forecasts locally are now common. However, their forecasts for each individual series remain isolated, failing to account for the current state of its neighbouring series. Multivariate models like multivariate attention and graph neural networks can explicitly incorporate inter-series information, thus addressing the shortcomings of global models. However, these techniques exhibit quadratic complexity per timestep, limiting scalability. This paper introduces the Context Neural Network, an efficient linear complexity approach for augmenting time series models with relevant contextual insights from neighbouring time series without significant computational overhead. The proposed method enriches predictive models by providing the target series with real-time information from its neighbours, addressing the limitations of global models, yet remaining computationally tractable for large datasets.