Ada-MoGE：一种自适应高斯专家混合模型用于时间序列预测
Ada-MoGE: Adaptive Mixture of Gaussian Expert Model for Time Series Forecasting
AI总结：
Ada-MoGE通过自适应确定专家数量和高斯带通滤波优化，提升时间序列预测的精度与效率。
摘要：
多变量时间序列预测被广泛应用于工业、交通运输和金融预测等领域。然而，时间序列中的主导频率可能随着数据的谱分布变化而变化。传统的专家混合（MoE）模型采用固定数量的专家，难以适应这些变化，导致频率覆盖不均衡的问题。具体来说，专家数量过少会导致关键信息被忽略，而专家数量过多则会引入噪声。为此，我们提出了Ada-MoGE，一种自适应高斯专家混合模型。Ada-MoGE整合了谱强度和频率响应，以自适应地确定专家数量，确保与输入数据的频率分布对齐。这种方法防止了由于专家数量不足而导致的信息损失，以及由于专家数量过多而引入的噪声污染。此外，为了防止直接带截断引入噪声，我们采用高斯带通滤波器对频率域特征进行平滑分解，进一步优化特征表示。实验结果表明，我们的模型在六个公开基准上仅使用0.2百万参数即可取得最先进的性能。
英文摘要：
Multivariate time series forecasts are widely used, such as industrial, transportation and financial forecasts. However, the dominant frequencies in time series may shift with the evolving spectral distribution of the data. Traditional Mixture of Experts (MoE) models, which employ a fixed number of experts, struggle to adapt to these changes, resulting in frequency coverage imbalance issue. Specifically, too few experts can lead to the overlooking of critical information, while too many can introduce noise. To this end, we propose Ada-MoGE, an adaptive Gaussian Mixture of Experts model. Ada-MoGE integrates spectral intensity and frequency response to adaptively determine the number of experts, ensuring alignment with the input data's frequency distribution. This approach prevents both information loss due to an insufficient number of experts and noise contamination from an excess of experts. Additionally, to prevent noise introduction from direct band truncation, we employ Gaussian band-pass filtering to smoothly decompose the frequency domain features, further optimizing the feature representation. The experimental results show that our model achieves state-of-the-art performance on six public benchmarks with only 0.2 million parameters.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
