# Changes by Butterflies: Farsighted Forecasting with Group Reservoir Transformer

arXiv: https://arxiv.org/abs/2402.09573 · HTML: https://mlsanity.com/paper/2402.09573/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 73 references that are in the map.
- First posted on arXiv 14 Feb 2024.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [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)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [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)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting](https://mlsanity.com/paper/1907.00235/) (2019)
- [Non-stationary Transformers: Exploring the Stationarity in Time Series Forecasting](https://mlsanity.com/paper/2205.14415/) (2022)
- [Adapting Language Models to Compress Contexts](https://mlsanity.com/paper/2305.14788/) (2023)
- [BRITS: Bidirectional Recurrent Imputation for Time Series](https://mlsanity.com/paper/1805.10572/) (2018)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [AutoFormer: Searching Transformers for Visual Recognition](https://mlsanity.com/paper/2107.00651/) (2021)
- [Next Generation Reservoir Computing](https://mlsanity.com/paper/2106.07688/) (2021)
- [ETSformer: Exponential Smoothing Transformers for Time-series Forecasting](https://mlsanity.com/paper/2202.01381/) (2022)
- [Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case](https://mlsanity.com/paper/2001.08317/) (2020)
- [LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters](https://mlsanity.com/paper/2308.08469/) (2023)
- [Unlimiformer: Long-Range Transformers with Unlimited Length Input](https://mlsanity.com/paper/2305.01625/) (2023)
- [Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks](https://mlsanity.com/paper/1711.08742/) (2017)

## Abstract (arXiv)

In Chaos, a minor divergence between two initial conditions exhibits exponential amplification over time, leading to far-away outcomes, known as the butterfly effect. Thus, the distant future is full of uncertainty and hard to forecast. We introduce Group Reservoir Transformer to predict long-term events more accurately and robustly by overcoming two challenges in Chaos: (1) the extensive historical sequences and (2) the sensitivity to initial conditions. A reservoir is attached to a Transformer to efficiently handle arbitrarily long historical lengths, with an extension of a group of reservoirs to reduce the sensitivity to the initialization variations. Our architecture consistently outperforms state-of-the-art models in multivariate time series, including TimeLLM, GPT2TS, PatchTST, DLinear, TimeNet, and the baseline Transformer, with an error reduction of up to -59% in various fields such as ETTh, ETTm, and air quality, demonstrating that an ensemble of butterfly learning can improve the adequacy and certainty of event prediction, despite of the traveling time to the unknown future.