提出模块化框架，精准定位时间序列预测模型的真正贡献组件。
CombinationTS: A Modular Framework for Understanding Time-Series Forecasting Models
- 将模型拆分为输入、嵌入、编码、解码等独立模块，统一评估条件。
- 发现无参数身份编码器常优于复杂模型，打破性能依赖复杂架构的迷思。
- 输入变换引入先验比增加编码器复杂度更优，适合模型设计参考。
时间序列预测模型架构日益复杂，但许多先进成果存在统计脆弱或归因错误。我们主张从模型选择转向模块归因，识别真正驱动性能的组件。提出CombinationTS，一个自包含的概率评估框架，将模型分解为正交模块——输入变换、嵌入、编码器、解码器和输出变换，并在共享评估条件下进行评估。通过边际性能（μ）和稳定性（σ）量化各组件表现，实现超越脆弱点估计的稳健归因。大规模成对实验揭示‘恒等悖论’：一旦嵌入设计合理，无参数的身份编码器往往可媲美甚至超越复杂主干。进一步表明，通过输入变换引入显式结构先验，相比提升编码器复杂度，能获得更优的性能-稳定性权衡，为架构必要性提供原则性基准。
原文摘要 · Abstract (English)
Recent progress in time-series forecasting has led to rapidly increasing architectural complexity, yet many reported State-of-the-Art gains are statistically fragile or misattributed. We argue that progress requires a shift from model selection to modular attribution, identifying which components truly drive performance. We propose CombinationTS, a self-contained probabilistic evaluation framework that decomposes forecasting models into orthogonal modules--Input Transformation, Embedding, Encoder, Decoder, and Output Transformation--and evaluates them under a shared evaluation condition space. By quantifying each component via marginalized performance ($μ$) and stability ($σ$), CombinationTS enables robust attribution beyond fragile point estimates. Through large-scale paired evaluation, we uncover the Identity Paradox: once the data view (Embedding) is well-designed, a parameter-free Identity Encoder often matches or outperforms complex backbones. We further show that explicit structural priors introduced via Input Transformations yield a more favorable performance-stability trade-off than increasing Encoder complexity, establishing a principled baseline for architectural necessity.
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。