融合多种顶尖时序模型，构建更强大的预测系统。
EMTSF:Extraordinary Mixture of SOTA Models for Time Series Forecasting
- 用Transformer门控网络混合xLSTM、PatchTST等先进模型
- 在标准数据集上超越所有现有时序预测模型
- 适合需要高精度时序预测的研究与工业应用
Transformer在自然语言处理中的成功推动了其在时序预测（TSF）领域的应用，展现出优异性能。然而，有研究指出简单的一层线性模型反而优于Transformer模型，随后提出的PatchTST证明该结论不成立。近期，基于大语言模型（LLM）的TimeLLM取得更优结果，但另一研究发现移除或替换其LLM组件反而性能更好。时序数据通常更依赖近期信息，且受不可预测事件影响。基于这些新见解，本文提出一种强混合专家（MoE）框架，集成xLSTM、增强线性模型、PatchTST、minGRU等多样化且互补的前沿模型，通过基于Transformer的门控网络进行融合。该方法在标准基准测试中全面超越现有时序预测模型，甚至优于其他基于MoE的最新方法。
原文摘要 · Abstract (English)
The immense success of the Transformer architecture in Natural Language Processing has led to its adoption in Time Se ries Forecasting (TSF), where superior performance has been shown. However, a recent important paper questioned their effectiveness by demonstrating that a simple single layer linear model outperforms Transformer-based models. This was soon shown to be not as valid, by a better transformer-based model termed PatchTST. More re cently, TimeLLM demonstrated even better results by repurposing a Large Language Model (LLM) for the TSF domain. Again, a follow up paper challenged this by demonstrating that removing the LLM component or replacing it with a basic attention layer in fact yields better performance. One of the challenges in forecasting is the fact that TSF data favors the more recent past, and is sometimes subject to unpredictable events. Based upon these recent insights in TSF, we propose a strong Mixture of Experts (MoE) framework. Our method combines the state-of-the-art (SOTA) models including xLSTM, en hanced Linear, PatchTST, and minGRU, among others. This set of complimentary and diverse models for TSF are integrated in a Trans former based MoE gating network. Our proposed model outperforms all existing TSF models on standard benchmarks, surpassing even the latest approaches based on MoE frameworks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。