# FreqLens: Interpretable Frequency Attribution for Time Series Forecasting

arXiv: https://arxiv.org/abs/2602.08768 · HTML: https://mlsanity.com/paper/2602.08768/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 9 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [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)

## Built on by (most cited first, 1 of 1)

- [Explaining Time Series Forecasting with Horizon-Resolved Attribution](https://mlsanity.com/paper/2609.12639/) (2026)

## Abstract (arXiv)

Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose textscFreqLens, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. textscFreqLens introduces two key innovations: (1) learnable frequency discovery -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) axiomatic frequency attribution -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, textscFreqLens achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle (24.6 ± 0.1h, 2.5% error) and 12-hour half-daily cycle (11.8 ± 0.1h, 1.6% error) on Traffic, and weekly cycles (10× longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.