用代表性样本全局解释时间序列模型行为，让专家轻松看懂。
INSIGHTS: Demonstration-Based Summaries of Time Series Predictors
- 基于样本重要性与多样性，生成能反映模型整体行为的代表性子集。
- 实验表明，该方法生成的样本集兼具全面性与可读性，便于人工评估。
- 特别适合需要理解模型长期行为的领域专家使用。
可解释性方法发展迅速，但针对时间序列模型的全局解释仍不充分，多数方法仅关注局部实例级归因。我们提出INSIGHTS，一种模型无关、以用户为中心的全局解释方法，强调设计上的简洁性、高效性与透明性，确保利益相关方易于采纳其输出。不同于现有方法聚焦局部解释，INSIGHTS通过生成样本摘要，提供对模型行为的全面概览。它利用捕捉领域特定特征（如超出领域标准）的效用函数，平衡样本的重要性与多样性，构建信息丰富的子集。我们在实验、访谈和用户研究中评估了INSIGHTS。结果表明，该方法能有效构建全面且多样化的时序样本子集，生成的摘要适于个体评估。领域专家更青睐其对模型行为的稳定理解及所识别样本的质量。此外，使用INSIGHTS摘要的用户在模型整体行为理解上表现显著提升。
原文摘要 · Abstract (English)
Explainability methods have progressed rapidly, but global explanations for time-series models remain underdeveloped, with most approaches focusing on local, instance-level attributions. We introduce INSIGHTS, a model-agnostic, user-centric approach for providing global explanations of time series models. Our approach prioritizes simplicity, efficiency, and transparency in its design, ensuring that stakeholders can readily adopt its outputs. While current methods focus on local explanations, INSIGHTS generates sample summaries that offer a comprehensive overview of model behavior. It balances the importance and diversity of time series samples to create informative subsets using utility functions that capture domain-specific aspects of time series behavior, such as exceeding domain norms. We evaluate INSIGHTS through experiments, interviews, and a user study. Our results indicate INSIGHTS effectively constructs comprehensive, diverse time series subsets, producing summaries manageable for individual evaluation. It is preferred by domain experts for its ability to provide a stable understanding of model behavior and the quality of the samples identified. Moreover, user study participants presented with INSIGHTS-based summaries exhibit an enhanced understanding of the model's overall behavior.
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。