# Learning Temporal Saliency for Time Series Forecasting with Cross-Scale Attention

arXiv: https://arxiv.org/abs/2509.22839 · HTML: https://mlsanity.com/paper/2509.22839/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 18 of 18)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [ETSformer: Exponential Smoothing Transformers for Time-series Forecasting](https://mlsanity.com/paper/2202.01381/) (2022)
- [Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey](https://mlsanity.com/paper/2104.00950/) (2021)
- [Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis](https://mlsanity.com/paper/1806.08946/) (2018)
- [Evaluation of post-hoc interpretability methods in time-series classification](https://mlsanity.com/paper/2202.05656/) (2022)
- [Exploring Interpretable LSTM Neural Networks over Multi-Variable Data](https://mlsanity.com/paper/1905.12034/) (2019)
- [Counterfactual Explanations for Time Series Forecasting](https://mlsanity.com/paper/2310.08137/) (2023)
- [XAI Methods for Neural Time Series Classification: A Brief Review](https://mlsanity.com/paper/2108.08009/) (2021)
- [EDformer: Embedded Decomposition Transformer for Interpretable Multivariate Time Series Predictions](https://mlsanity.com/paper/2412.12227/) (2024)
- [LMS-AutoTSF: Learnable Multi-Scale Decomposition and Integrated Autocorrelation for Time Series Forecasting](https://mlsanity.com/paper/2412.06866/) (2024)

## Abstract (arXiv)

Explainability in time series forecasting is essential for improving model transparency and supporting informed decision-making. In this work, we present CrossScaleNet, an innovative architecture that combines a patch-based cross-attention mechanism with multi-scale processing to achieve both high performance and enhanced temporal explainability. By embedding attention mechanisms into the training process, our model provides intrinsic explainability for temporal saliency, making its decision-making process more transparent. Traditional post-hoc methods for temporal saliency detection are computationally expensive, particularly when compared to feature importance detection. While ablation techniques may suffice for datasets with fewer features, identifying temporal saliency poses greater challenges due to its complexity. We validate CrossScaleNet on synthetic datasets with known saliency ground truth and on established public benchmarks, demonstrating the robustness of our method in identifying temporal saliency. Experiments on real-world datasets for forecasting task show that our approach consistently outperforms most transformer-based models, offering better explainability without sacrificing predictive accuracy. Our evaluations demonstrate superior performance in both temporal saliency detection and forecasting accuracy. Moreover, we highlight that existing models claiming explainability often fail to maintain strong performance on standard benchmarks. CrossScaleNet addresses this gap, offering a balanced approach that captures temporal saliency effectively while delivering state-of-the-art forecasting performance across datasets of varying complexity.