EVOTS: 面向时间序列预测的进化Transformer搜索
EVOTS: Evolutionary Transformer Search for Time Series Forecasting
AI总结：
提出进化神经架构搜索框架EVOTS，通过模块化基因组表示和修复机制自动发现任务自适应的Transformer类架构，在ETT数据集多变量预测中达到竞争性性能。
摘要：
多变量时间序列预测的进化神经架构设计仍未被充分探索，尽管任务和预测设置存在显著差异，大多数方法仍依赖固定的Transformer架构。本文引入了一个进化神经架构搜索框架，用于发现任务自适应的Transformer类时间序列预测模型（EVOTS）。架构使用模块化基因组表示进行编码，该表示能够灵活组合注意力、前馈和投影组件，同时通过修复机制在整个进化过程中确保结构有效性。这种公式允许在不依赖手工设计规则的情况下有效探索多样化的架构空间。所提方法在ETT家族（ETTh1、ETTh2、ETTm1和ETTm2）的四个基准数据集上进行了评估，涵盖了多种预测设置，包括单变量到单变量、多变量到单变量以及多变量到多变量预测，预测视野为96、192、336和720。在多变量到多变量设置中，进化架构相对于强大的基于Transformer的基线实现了有竞争力的均方误差，并且在多个案例中有所改进。进一步的分析考察了不同预测设置下的性能差异，并报告了挂钟训练时间以粗略指示计算成本。总体而言，结果表明进化搜索能够在实际运行时间约束内有效发现灵活且高性能的Transformer类架构，用于多变量时间序列预测。
英文摘要：
Evolutionary neural architecture design for multivariate time-series forecasting remains underexplored, with most approaches relying on fixed Transformer architectures despite substantial variation across tasks and forecasting settings. This paper introduces an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for time-series forecasting (EVOTS). Architectures are encoded using a modular genome representation that enables flexible composition of attention, feed-forward, and projection components, while a repair mechanism enforces structural validity throughout the evolutionary process. This formulation allows effective exploration of a diverse architecture space without relying on hand-crafted design rules. The proposed approach is evaluated on four benchmark datasets from the ETT family (ETTh1, ETTh2, ETTm1, and ETTm2) under multiple forecasting settings, including univariate-to-univariate, multivariate-to-univariate, and multivariate-to-multivariate prediction, with horizons of 96, 192, 336, and 720. In the multivariate-to-multivariate setting, the evolved architectures achieve competitive and, in several cases, improved mean squared error relative to a strong Transformer-based baseline. Additional analyses examine performance differences across forecasting settings and report wall-clock training time to provide a coarse indication of computational cost. Overall, the results demonstrate that evolutionary search can effectively discover flexible and high-performing Transformer-like architectures for multivariate time-series forecasting within practical runtime constraints.
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。
