生成更真实可信的时间序列反事实解释，提升模型可解释性。
GenFacts-Generative Counterfactual Explanations for Multi-Variate Time Series
- 基于判别式变分自编码器生成反事实样本，融合对比学习与一致性约束。
- 在雷达手势和手写轨迹数据上，真实性提升18.7%，人类评估得分最高。
- 适合需要真实可信解释的工业场景，如医疗、金融时序分析。
反事实解释通过展示输入如何被最小修改以改变预测结果，提升模型透明度。针对多变量时间序列，现有方法生成的反事实常无效、不自然或难以理解。我们提出GenFacts，一种基于类判别变分自编码器的生成框架，整合对比学习、分类一致性目标、基于原型的初始化及现实性约束优化。我们在雷达手势数据（工业应用）和手写字母轨迹数据（直观基准）上评估该方法。在两个数据集上，GenFacts在真实性上优于最先进基线方法18.7%，并在人类研究中取得最高可解释性评分。结果表明，对于时间序列数据，可行动的反事实解释关键在于真实性与用户中心的可解释性，而非仅追求稀疏性。
原文摘要 · Abstract (English)
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.
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。