Learning Perturbations to Explain Time Series Predictions
This work addresses the challenge of providing interpretable explanations for time series predictions, which is crucial for domains like healthcare or finance, but it is incremental as it builds on existing perturbation-based methods.
The paper tackled the problem of explaining predictions on multivariate time series data by learning both masks and perturbations, rather than using fixed perturbations as in prior work, and empirically showed that this approach significantly improves explanation quality.
Explaining predictions based on multivariate time series data carries the additional difficulty of handling not only multiple features, but also time dependencies. It matters not only what happened, but also when, and the same feature could have a very different impact on a prediction depending on this time information. Previous work has used perturbation-based saliency methods to tackle this issue, perturbing an input using a trainable mask to discover which features at which times are driving the predictions. However these methods introduce fixed perturbations, inspired from similar methods on static data, while there seems to be little motivation to do so on temporal data. In this work, we aim to explain predictions by learning not only masks, but also associated perturbations. We empirically show that learning these perturbations significantly improves the quality of these explanations on time series data.