PAX-TS: Model-agnostic multi-granular explanations for time series forecasting via localized perturbations

Tim Kreuzer, Jelena Zdravkovic, Panagiotis Papapetrou

Keywords: Time series forecasting, explainability, perturbation

TL;DR: PAX-TS is a novel post-hoc explainability method for multi-granular explanations, designed for time series forecasting

Abstract: Time series forecasting has seen considerable improvement during the last years, with transformer models and large language models driving advancements of the state of the art. Modern forecasting models are generally opaque and do not provide explanations for their forecasts, while well-known post-hoc explainability methods like LIME are not suitable for the forecasting context. We propose PAX-TS, a model-agnostic post-hoc algorithm to explain time series forecasting models and their forecasts. Our method is based on localized input perturbations and results in multi-granular explanations. Further, it is able to characterize cross-channel correlations for multivariate time series forecasts. We compare our algorithm with two other state-of-the-art explanation algorithms and present the different explanation types of the method. We found that the explanations of high-performing and low-performing algorithms differ on the same datasets, highlighting that the explanations of PAX-TS effectively capture a model's behavior. Based on time step correlation matrices resulting from the benchmark, we identify 6 classes of patterns that repeatedly occur across different datasets and algorithms. We found that the patterns are indicators of performance, with noticeable differences in forecasting error between the classes. With PAX-TS, time series forecasting models' mechanisms can be illustrated in different levels of detail, and its explanations can be used to answer practical questions on forecasts.

Primary Area: interpretability and explainable AI

Submission Number: 14164