为实时场景设计可解释模型，快速生成可信的解释示例。
Explainable AI in Time-Sensitive Scenarios: Prefetched Offline Explanation Model
- 离线预生成解释基底，推理时快速匹配测试样本。
- 比前代Abele快，生成更丰富多样的示例和更清晰的显著图。
- 适合医疗、自动驾驶等对时效性要求高的领域使用。
随着预测性机器学习模型日益普及与复杂，其角色已从单纯预测结果演变为主动影响决策。这一转变凸显了可信AI的重要性，强调需超越准确率，深入理解模型在具体应用情境中的行为。为推进可解释性研究，本文提出Poem（Prefetched Offline Explanation Model），一种针对图像数据的模型无关、局部可解释性算法。该算法生成实例、反例及显著图，以支持时间敏感场景下的快速有效解释。Poem基于现有局部算法，从数据中推断真实与反事实规则，通过设计增强稳定性，生成具有代表性的示例与相反情景。创新机制将输入测试点与预存解释库匹配，输出多样化实例、信息丰富的显著图及可信反例。实验表明，Poem在速度上优于前代Abele，能生成更精细、更多样化的实例，以及更具洞察力的显著图和有价值的反例。
原文摘要 · Abstract (English)
As predictive machine learning models become increasingly adopted and advanced, their role has evolved from merely predicting outcomes to actively shaping them. This evolution has underscored the importance of Trustworthy AI, highlighting the necessity to extend our focus beyond mere accuracy and toward a comprehensive understanding of these models' behaviors within the specific contexts of their applications. To further progress in explainability, we introduce Poem, Prefetched Offline Explanation Model, a model-agnostic, local explainability algorithm for image data. The algorithm generates exemplars, counterexemplars and saliency maps to provide quick and effective explanations suitable for time-sensitive scenarios. Leveraging an existing local algorithm, \poem{} infers factual and counterfactual rules from data to create illustrative examples and opposite scenarios with an enhanced stability by design. A novel mechanism then matches incoming test points with an explanation base and produces diverse exemplars, informative saliency maps and believable counterexemplars. Experimental results indicate that Poem outperforms its predecessor Abele in speed and ability to generate more nuanced and varied exemplars alongside more insightful saliency maps and valuable counterexemplars.
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。