无需模型即可从实时数据中高效选出高质量反事实样本
Model-Free Counterfactual Subset Selection at Scale
- 直接从真实观测数据中选择反事实样本，无需依赖假设或合成数据
- 每条数据更新仅需O(log k)复杂度，适合大规模流式数据处理
- 在真实与对抗性场景下表现稳健，适合需要实时解释的系统
确保AI决策透明性需要实例级可解释性。反事实解释是有效工具，但现有方法常依赖合成样本，引入不切实际假设、模型缺陷或数据偏差。许多方法还假设可获取完整数据集，这在实时数据流环境中不现实。相比之下，流式解释可在无需长期存储全量数据的前提下提供动态洞察。本文提出一种可扩展的、无需模型的反事实子集选择方法，直接从观测数据中选取多样且相关的反事实样本。算法在流式场景下高效运行，每条数据更新时间复杂度为O(log k)，并保证高质量选择。在真实与合成数据集上的实证评估表明，该方法优于基线，且在对抗条件下仍具鲁棒性。
原文摘要 · Abstract (English)
Ensuring transparency in AI decision-making requires interpretable explanations, particularly at the instance level. Counterfactual explanations are a powerful tool for this purpose, but existing techniques frequently depend on synthetic examples, introducing biases from unrealistic assumptions, flawed models, or skewed data. Many methods also assume full dataset availability, an impractical constraint in real-time environments where data flows continuously. In contrast, streaming explanations offer adaptive, real-time insights without requiring persistent storage of the entire dataset. This work introduces a scalable, model-free approach to selecting diverse and relevant counterfactual examples directly from observed data. Our algorithm operates efficiently in streaming settings, maintaining $O(\log k)$ update complexity per item while ensuring high-quality counterfactual selection. Empirical evaluations on both real-world and synthetic datasets demonstrate superior performance over baseline methods, with robust behavior even under adversarial conditions.
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。