GenFacts-多变量时间序列的生成性反事实解释
GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
AI总结：
GenFacts通过生成多变量时间序列的反事实解释，提升了反事实的合理性和用户可解释性，优于现有方法。
摘要：
反事实解释旨在通过展示如何最小地改变输入以改变预测来增强模型的透明性。对于多变量时间序列，现有方法生成的反事实往往无效、不合情理或不直观。我们引入了GenFacts，这是一种基于类别判别变分自编码器的生成框架。它集成了对比和分类一致性目标、基于原型的初始化以及现实约束优化。我们在雷达手势数据作为工业用例和手写字母轨迹作为直观基准上评估了GenFacts。在两个数据集上，GenFacts在合理性（+18.7%）方面优于最先进的基线，并在人类研究中实现了最高的可解释性评分。这些结果表明，合理性与以用户为中心的可解释性，而非稀疏性本身，是时间序列数据中可行反事实的关键。
英文摘要：
Counterfactual explanations aim to enhance model transparency by showing how inputs can be minimally altered to change predictions. For multivariate time series, existing methods often generate counterfactuals that are invalid, implausible, or unintuitive. We introduce GenFacts, a generative framework based on a class-discriminative variational autoencoder. It integrates contrastive and classification-consistency objectives, prototype-based initialization, and realism-constrained optimization. We evaluate GenFacts on radar gesture data as an industrial use case and handwritten letter trajectories as an intuitive benchmark. Across both datasets, GenFacts outperforms state-of-the-art baselines in plausibility (+18.7%) and achieves the highest interpretability scores in a human study. These results highlight that plausibility and user-centered interpretability, rather than sparsity alone, are key to actionable counterfactuals in time series data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
