用因果稀疏自编码器提升时序模型解释的可信度与泛化能力
TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
- 结合稀疏自编码器与因果推理，构建可解释框架
- 在合成与真实数据上均优于现有方法，解释更忠实可靠
- 适合高风险场景下需要可信解释的时序模型应用
随着黑箱模型和预训练模型在时序任务中日益普及，理解并解释其预测结果变得愈发重要，尤其在对可解释性与信任度要求高的领域。然而，多数现有方法仅限于分布内解释，缺乏分布外泛化能力。本文提出TimeSAE框架，融合稀疏自编码器（SAE）与因果性思想，用于时序黑箱模型的解释。实验表明，当前许多解释方法对分布偏移敏感，而TimeSAE在合成与真实时序数据集上均表现更优，通过定量指标与定性分析验证了其解释的忠实性与鲁棒性。代码已开源至TimeSAE-Lib：https://oublalkhalid.github.io/TimeSAE/
原文摘要 · Abstract (English)
As black box models and pretrained models gain traction in time series applications, understanding and explaining their predictions becomes increasingly vital, especially in high-stakes domains where interpretability and trust are essential. However, most of the existing methods involve only in-distribution explanation, and do not generalize outside the training support, which requires the learning capability of generalization. In this work, we aim to provide a framework to explain black-box models for time series data through the dual lenses of Sparse Autoencoders (SAEs) and causality. We show that many current explanation methods are sensitive to distributional shifts, limiting their effectiveness in real-world scenarios. Building on the concept of Sparse Autoencoder, we introduce TimeSAE, a framework for black-box model explanation. We conduct extensive evaluations of TimeSAE on both synthetic and real-world time series datasets, comparing it to leading baselines. The results, supported by both quantitative metrics and qualitative insights, show that TimeSAE provides more faithful and robust explanations. Our code is available in an easy-to-use library TimeSAE-Lib: https://oublalkhalid.github.io/TimeSAE/
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。