Scholarlink

<p>Long-Term Time Series Forecasting requires robust learning under nonstationarity, noisy gradients, and delayed adaptation caused by distribution shifts. Evolutionary-Guided Module Fusion with Gradient Refinement (EGMF-GR) is an architecture-agnostic training framework that combines population-based global exploration with gradient-based local refinement, rather than introducing a new forecasting architecture. During training, aligned modules between the current individual and the global best individual are monitored, and their discrepancies are evaluated using multiple complementary criteria. An interquartile range based hybrid threshold determines whether each module state is fused or retained. Fusion is performed at the module state level by merging learnable parameters and synchronizing non-learnable buffers, which reduces state inconsistency after merging and improves optimization stability. Experiments on eight public benchmarks demonstrate that EGMF-GR improves forecasting accuracy and training stability under a controlled optimization budget.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Hybrid evolutionary-gradient training improves long-term time series forecasting

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月29日

查看全文
  • Lihong Zhao,
  • Zhihui Chen,
  • Naiqi Wu,
  • Liping Bai

摘要

Long-Term Time Series Forecasting requires robust learning under nonstationarity, noisy gradients, and delayed adaptation caused by distribution shifts. Evolutionary-Guided Module Fusion with Gradient Refinement (EGMF-GR) is an architecture-agnostic training framework that combines population-based global exploration with gradient-based local refinement, rather than introducing a new forecasting architecture. During training, aligned modules between the current individual and the global best individual are monitored, and their discrepancies are evaluated using multiple complementary criteria. An interquartile range based hybrid threshold determines whether each module state is fused or retained. Fusion is performed at the module state level by merging learnable parameters and synchronizing non-learnable buffers, which reduces state inconsistency after merging and improves optimization stability. Experiments on eight public benchmarks demonstrate that EGMF-GR improves forecasting accuracy and training stability under a controlled optimization budget.