面向时间序列解释的统一信息瓶颈框架
Towards A Unified Information Bottleneck Framework for Time Series Explanations
另 2 家 · 查看机构详情
- Florida International University（佛罗里达国际大学）
- Carnegie Mellon University（卡内基梅隆大学）
- University of Houston（休斯顿大学）
- NEC Labs America（美国 NEC 实验室）
- Singapore Management University（新加坡管理大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本研究针对时间序列解释的现有方法存在的局限，提出统一信息瓶颈框架，引入ModelName，在合成与真实基准上均优于现有方法，可生成忠实归因与稳定反事实解释。
中文摘要 AI 辅助
解释对时间序列数据进行操作的深度学习模型，在需要对模型行为获得透明且可解释见解的各类应用中至关重要。现有解释方法大致分为两类：归因式解释，用于识别对预测最具影响的时间区域；反事实解释，用于揭示应如何修改输入以改变模型的决策。尽管这些方法能提供有价值的见解，但两个领域大多是独立研究的。这种脱节导致归因方法缺乏因果验证，而反事实方法则存在严重的不稳定性，会产生类似对抗性的噪声而非有意义的解释。在本研究中，我们从信息论视角重新审视时间序列可解释性，发现现有解释器易受平凡解和分布偏移的影响。为解决这些局限，我们提出了一个可解释时间序列学习的统一目标函数，在单一框架内桥接归因与反事实推理。基于信息瓶颈原理，我们的公式明确防止了平凡解释和分布外反事实。基于该目标函数，我们引入了{\textbf{ModelName}}这一新型解释框架，该框架学习参数化变换网络以构建嵌入解释的实例，其中保留的信息生成归因解释，而受控的信息移除则产生稳定的反事实解释。我们在合成基准和真实基准上，将{\textbf{ModelName}}与最先进的基线进行了评估。大量定量和定性结果表明，{\textbf{ModelName}}始终优于对比方法，能生成忠实的归因和稳定的反事实解释。
英文摘要
Explaining deep learning models operating on time series data is crucial in various applications that require transparent and interpretable insights into model behavior. {Existing explanation methods generally fall into two categories: attribution-based explanations, which identify the temporal regions most responsible for a prediction, and counterfactual explanations, which reveal how an input should be modified to alter the model's decision.} {Despite valuable insights, these two fields are largely studied independently. This disconnect leaves attribution methods lacking causal validation, while counterfactual methods suffer from severe instability, producing adversarial-like noise instead of meaningful explanations.} In this work, we revisit time-series explainability from an information-theoretic perspective and show that existing explainers are vulnerable to trivial solutions and distributional shifts. To address these limitations, we propose a unified objective function for explainable time series learning that bridges attribution and counterfactual reasoning within a single framework. Building upon the Information Bottleneck principle, our formulation explicitly prevents trivial explanations and out-of-distribution counterfactuals. {Based on this objective function, we introduce {\modelname}, a novel explanation framework that learns a parametric transformation network to construct explanation-embedded instances, where preserved information yields attribution explanations and controlled information removal produces stable counterfactual explanations.} We evaluate {\modelname} on synthetic and real-world benchmarks against state-of-the-art baselines. Extensive quantitative and qualitative results show that {\modelname} consistently outperforms competing methods, yielding faithful attributions and stable counterfactual explanations.
