RECOWNs: Probabilistic Circuits for Trustworthy Time Series Forecasting

TL;DR

RECOWNs combine RNNs with probabilistic circuits to enhance trustworthiness in time series forecasting by providing meaningful uncertainty estimates, enabling better detection of unreliable predictions.

Contribution

The paper introduces RECOWN, a novel architecture integrating RNNs with Conditional WSPNs for trustworthy time series forecasting with uncertainty quantification.

Findings

RECOWNs achieve high accuracy in time series prediction.

RECOWNs effectively identify uncertain or unreliable predictions.

The proposed method outperforms traditional RNNs in trustworthiness metrics.

Abstract

Time series forecasting is a relevant task that is performed in several real-world scenarios such as product sales analysis and prediction of energy demand. Given their accuracy performance, currently, Recurrent Neural Networks (RNNs) are the models of choice for this task. Despite their success in time series forecasting, less attention has been paid to make the RNNs trustworthy. For example, RNNs can not naturally provide an uncertainty measure to their predictions. This could be extremely useful in practice in several cases e.g. to detect when a prediction might be completely wrong due to an unusual pattern in the time series. Whittle Sum-Product Networks (WSPNs), prominent deep tractable probabilistic circuits (PCs) for time series, can assist an RNN with providing meaningful probabilities as uncertainty measure. With this aim, we propose RECOWN, a novel architecture that employs RNNs and a discriminant variant of WSPNs called Conditional WSPNs (CWSPNs). We also formulate a Log-Likelihood Ratio Score as better estimation of uncertainty that is tailored to time series and Whittle likelihoods. In our experiments, we show that RECOWNs are accurate and trustworthy time series predictors, able to "know when they do not know".