# GBT: Two-stage transformer framework for non-stationary time series forecasting

arXiv: https://arxiv.org/abs/2307.08302 · HTML: https://mlsanity.com/paper/2307.08302/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 48 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [N-BEATS: Neural basis expansion analysis for interpretable time series forecasting](https://mlsanity.com/paper/1905.10437/) (2019)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction](https://mlsanity.com/paper/2106.09305/) (2021)
- [Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structures](https://mlsanity.com/paper/2207.01186/) (2022)
- [FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting](https://mlsanity.com/paper/2205.08897/) (2022)
- [N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting](https://mlsanity.com/paper/2201.12886/) (2022)
- [CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting](https://mlsanity.com/paper/2202.01575/) (2022)
- [AirFormer: Predicting Nationwide Air Quality in China with Transformers](https://mlsanity.com/paper/2211.15979/) (2022)
- [Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Version](https://mlsanity.com/paper/2203.15737/) (2022)
- [Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Version](https://mlsanity.com/paper/2204.13767/) (2022)
- [TCN: Table Convolutional Network for Web Table Interpretation](https://mlsanity.com/paper/2102.09460/) (2021)
- [Empirical Quantitative Analysis of COVID-19 Forecasting Models](https://mlsanity.com/paper/2110.00174/) (2021)
- [Human Activity Recognition using Multi-Head CNN followed by LSTM](https://mlsanity.com/paper/2003.06327/) (2020)
- [Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect](https://mlsanity.com/paper/2207.10941/) (2022)

## Built on by (most cited first, 8 of 8)

- [Are KANs Effective for Multivariate Time Series Forecasting?](https://mlsanity.com/paper/2408.11306/) (2024)
- [GARNN: An Interpretable Graph Attentive Recurrent Neural Network for Predicting Blood Glucose Levels via Multivariate Time Series](https://mlsanity.com/paper/2402.16230/) (2024)
- [Enhancing Multi-Step Brent Oil Price Forecasting with Ensemble Multi-Scenario Bi-GRU Networks](https://mlsanity.com/paper/2407.11267/) (2024)
- [Non-stationary BERT: Exploring Augmented IMU Data For Robust Human Activity Recognition](https://mlsanity.com/paper/2409.16730/) (2024)
- [Self-Supervised Learning for Time Series: A Review & Critique of FITS](https://mlsanity.com/paper/2410.18318/) (2024)
- [Wavelet-Enhanced Neural ODE and Graph Attention for Interpretable Energy Forecasting](https://mlsanity.com/paper/2507.10132/) (2025)
- [Adaptive Normalization Mamba with Multi Scale Trend Decomposition and Patch MoE Encoding](https://mlsanity.com/paper/2512.06929/) (2025)
- [Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting](https://mlsanity.com/paper/2610.19603/) (2026)

## Abstract (arXiv)

This paper shows that time series forecasting Transformer (TSFT) suffers from severe over-fitting problem caused by improper initialization method of unknown decoder inputs, esp. when handling non-stationary time series. Based on this observation, we propose GBT, a novel two-stage Transformer framework with Good Beginning. It decouples the prediction process of TSFT into two stages, including Auto-Regression stage and Self-Regression stage to tackle the problem of different statistical properties between input and prediction sequences.Prediction results of Auto-Regression stage serve as a Good Beginning, i.e., a better initialization for inputs of Self-Regression stage. We also propose Error Score Modification module to further enhance the forecasting capability of the Self-Regression stage in GBT. Extensive experiments on seven benchmark datasets demonstrate that GBT outperforms SOTA TSFTs (FEDformer, Pyraformer, ETSformer, etc.) and many other forecasting models (SCINet, N-HiTS, etc.) with only canonical attention and convolution while owning less time and space complexity. It is also general enough to couple with these models to strengthen their forecasting capability. The source code is available at: https://github.com/OrigamiSL/GBT