AI 中文总结
针对现有可解释时间序列预测器忠实性不足的问题，提出IB-Forecast框架，其通过分解预测分量与信息瓶颈优化，在保证预测精度的同时提供高忠实度解释，性能优于多种基线方法。
AI 中文摘要
随着预测结果日益驱动能源、交通、医疗等领域的决策，理解这些预测背后的历史数据已与预测本身同等重要。尽管现有可内置解释性的预测器能揭示其内部结构，但无法保证这些结构忠实反映驱动预测的底层证据。相比之下，面向忠实性的方法虽会显式验证模型行为，却几乎仅针对事后分类任务设计。为弥合这一差距，我们提出IB-Forecast，这是一种本质可解释的多元时间序列预测框架。它将预测分解为学习到的周期分量和通过输入标记上的可解释掩码计算的残差分量。借助受预算约束的信息瓶颈，端到端优化使用户可直接控制解释稀疏度。通过严格的忠实性评估协议，大量实验表明，IB-Forecast在达到领先黑箱模型预测误差的同时，提供忠实解释且无额外推理成本。此外，在匹配的稀疏度预算下，这些原生解释在所有评估数据集上均持续优于基于梯度、基于遮挡和基于优化的基线。最终，现有可解释预测器的原生解释表现出较差的忠实性，而IB-Forecast保证高解释保真度，仅需14-20%的观测值即可实现低误差预测。
英文摘要
As forecasts increasingly drive decisions in fields such as energy, transportation, and healthcare, understanding the historical data behind these predictions has become as crucial as the predictions themselves. Although existing interpretable-by-design forecasters reveal their internal structures, they offer no guarantee that these structures faithfully reflect the underlying evidence driving the predictions. In contrast, while faithfulness-oriented methods explicitly verify model behavior, they are almost exclusively designed for post-hoc classification tasks. To bridge this gap, we propose IB-Forecast, an inherently interpretable multivariate time-series forecasting framework. It decomposes forecasting into a learned periodic component and a residual component computed with explainable masks over input tokens. With a budget-constrained information bottleneck, end-to-end optimization enables users to directly control explanation sparsity. With a rigorous faithfulness evaluation protocol, extensive experiments demonstrate that IB-Forecast matches the forecasting error of leading black-box models while providing faithful explanations at no additional inference cost. Furthermore, under a matched sparsity budget, these native explanations consistently surpass gradient-based, occlusion-based, and optimization-based baselines across all evaluated datasets. Ultimately, whereas the native explanations of existing interpretable forecasters exhibit poor faithfulness, IB-Forecast guarantees high explanation fidelity, requiring only 14-20% of the observations to deliver low-error predictions.
Comments17 pages, 6 figures, 8 tables
