# FTS: A Framework to Find a Faithful TimeSieve

arXiv: https://arxiv.org/abs/2405.19647 · HTML: https://mlsanity.com/paper/2405.19647/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 45 references that are in the map.
- First posted on arXiv 30 May 2024.

## Builds on (most cited first, 20 of 20)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [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)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)
- [Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks](https://mlsanity.com/paper/1701.05923/) (2017)
- [Frequency-domain MLPs are More Effective Learners in Time Series Forecasting](https://mlsanity.com/paper/2311.06184/) (2023)
- [Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors](https://mlsanity.com/paper/2305.18803/) (2023)
- [RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks](https://mlsanity.com/paper/2002.09545/) (2020)
- [LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version](https://mlsanity.com/paper/2302.12721/) (2023)
- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [SEAT: Stable and Explainable Attention](https://mlsanity.com/paper/2211.13290/) (2022)
- [SATO: Stable Text-to-Motion Framework](https://mlsanity.com/paper/2405.01461/) (2024)
- [Robust Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2202.11910/) (2022)
- [A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis](https://mlsanity.com/paper/2310.11959/) (2023)
- [Bayesian Median Autoregression for Robust Time Series Forecasting](https://mlsanity.com/paper/2001.01116/) (2020)

## Built on by (most cited first, 7 of 7)

- [DRIVE: Dependable Robust Interpretable Visionary Ensemble Framework in Autonomous Driving](https://mlsanity.com/paper/2409.10330/) (2024)
- [Enhanced Credit Score Prediction Using Ensemble Deep Learning Model](https://mlsanity.com/paper/2410.00256/) (2024)
- [Applications and Effect Evaluation of Generative Adversarial Networks in Semi-Supervised Learning](https://mlsanity.com/paper/2505.19522/) (2025)
- [CCSRP: Robust Pruning of Spiking Neural Networks through Cooperative Coevolution](https://mlsanity.com/paper/2408.00794/) (2024)
- [Case-based reasoning approach for diagnostic screening of children with developmental delays](https://mlsanity.com/paper/2408.02073/) (2024)
- [A High-Performance Thermal Infrared Object Detection Framework with Centralized Regulation](https://mlsanity.com/paper/2505.10825/) (2025)
- [Machine Learning Algorithm for Noise Reduction and Disease-Causing Gene Feature Extraction in Gene Sequencing Data](https://mlsanity.com/paper/2505.19740/) (2025)

## Abstract (arXiv)

The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive performance. However, an analysis reveals certain unfaithfulness issues, including high sensitivity to random seeds and minute input noise perturbations. Recognizing these challenges, we embark on a quest to define the concept of textbfunderlineFaithful underlineTimeunderlineSieve underline(FTS), a model that consistently delivers reliable and robust predictions. To address these issues, we propose a novel framework aimed at identifying and rectifying unfaithfulness in TimeSieve. Our framework is designed to enhance the model's stability and resilience, ensuring that its outputs are less susceptible to the aforementioned factors. Experimentation validates the effectiveness of our proposed framework, demonstrating improved faithfulness in the model's behavior. Looking forward, we plan to expand our experimental scope to further validate and optimize our algorithm, ensuring comprehensive faithfulness across a wide range of scenarios. Ultimately, we aspire to make this framework can be applied to enhance the faithfulness of not just TimeSieve but also other state-of-the-art temporal methods, thereby contributing to the reliability and robustness of temporal modeling as a whole.