AdaRNN: Adaptive Learning and Forecasting of Time Series
This addresses the challenge of distribution shifts in time series data for applications like activity recognition and finance, offering a novel framework that is incremental in adapting existing methods.
The paper tackles the problem of temporal covariate shift in time series forecasting by proposing AdaRNN, an adaptive model that uses temporal distribution characterization and matching to improve generalization, achieving a 2.6% increase in classification accuracy and a 9.0% reduction in RMSE compared to state-of-the-art methods.
Time series has wide applications in the real world and is known to be difficult to forecast. Since its statistical properties change over time, its distribution also changes temporally, which will cause severe distribution shift problem to existing methods. However, it remains unexplored to model the time series in the distribution perspective. In this paper, we term this as Temporal Covariate Shift (TCS). This paper proposes Adaptive RNNs (AdaRNN) to tackle the TCS problem by building an adaptive model that generalizes well on the unseen test data. AdaRNN is sequentially composed of two novel algorithms. First, we propose Temporal Distribution Characterization to better characterize the distribution information in the TS. Second, we propose Temporal Distribution Matching to reduce the distribution mismatch in TS to learn the adaptive TS model. AdaRNN is a general framework with flexible distribution distances integrated. Experiments on human activity recognition, air quality prediction, and financial analysis show that AdaRNN outperforms the latest methods by a classification accuracy of 2.6% and significantly reduces the RMSE by 9.0%. We also show that the temporal distribution matching algorithm can be extended in Transformer structure to boost its performance.