We are introducing a saliency map method that produces meaningful attributions for time-series ML models. Instead of restricting explanations to the raw time domain, our approach generates saliency maps in relevant domains such as frequency or ICA components – improving interpretability when applying deep models to time-domain signals.
Why it matters
Standard attribution methods (e.g. Integrated Gradients) yield point-wise importance in the time domain, which can be difficult to interpret in neuroscience. Our method extends this idea to domains that have semantic meaning in time-series applications.
Key features
Cross-Domain Saliency Maps is an open-source toolkit that:
- Provides frequency and ICA domain attributions out-of-the-box
- Extends to any invertible transform with a differentiable inverse
- Works plug-and-play with TensorFlow, no model retraining required
- Demonstrates utility on classification, regression, and forecasting models
Try it out
- Get the code and run it on your models (GitHub, check examples) GitHub - esl-epfl/cross-domain-saliency-maps: Pytorch/Tensorflow package for generating saliency maps for time-series models using Cross-Domain Integrated Gradients.
- Read the full story (arxiv preprint) https://arxiv.org/pdf/2505.13100