可迁移的可解释性AI：通过解释迁移在不同领域间建立理解
Transferable XAI: Relating Understanding Across Domains with Explanation Transfer
AI总结：
本文提出可迁移XAI框架，通过解释迁移在不同领域间建立理解，提升AI决策的可解释性和可重用性。
摘要：
当前的可解释性AI（XAI）专注于解释单一应用，但当遇到相关应用时，用户可能依赖他们以前的理解。这导致了过度泛化和AI过度依赖，或者负担沉重的独立记忆。实际上，相关决策任务可以共享解释因素，但有一些显著差异；例如，体重指数（BMI）对心脏病和糖尿病的风险影响相同，但胸痛更典型地提示心脏病。同样，使用不同属性完成相同任务的模型仍然共享信号；例如，温度和压力影响空气污染，但方向相反，由于理想气体定律。利用学习迁移，我们提出可迁移的XAI，以使用户能够通过使用通用仿射变换框架对线性因素解释进行解释，从而在相关领域之间转移理解。该框架支持在各种领域类型之间进行解释迁移：翻译用于数据子空间（包含先前增量XAI的工作），缩放用于决策任务，以及映射用于属性。重点是任务和属性领域类型，在形成性和总结性用户研究中，我们研究了参与者如何能够从一个领域转移到另一个领域理解AI决策。与单一领域和领域无关的解释相比，可迁移的XAI在理解第二个领域方面最有帮助，导致最佳的决策忠实度、因素回忆能力和在领域之间相关解释的能力。该框架通过解释子空间、任务和属性之间的因素关系，提高了在相关AI应用中解释的可重用性。
英文摘要：
Current Explainable AI (XAI) focuses on explaining a single application, but when encountering related applications, users may rely on their prior understanding from previous explanations. This leads to either overgeneralization and AI overreliance, or burdensome independent memorization. Indeed, related decision tasks can share explanatory factors, but with some notable differences; e.g., body mass index (BMI) affects the risks for heart disease and diabetes at the same rate, but chest pain is more indicative of heart disease. Similarly, models using different attributes for the same task still share signals; e.g., temperature and pressure affect air pollution but in opposite directions due to the ideal gas law. Leveraging transfer of learning, we propose Transferable XAI to enable users to transfer understanding across related domains by explaining the relationship between domain explanations using a general affine transformation framework applied to linear factor explanations. The framework supports explanation transfer across various domain types: translation for data subspace (subsuming prior work on Incremental XAI), scaling for decision task, and mapping for attributes. Focusing on task and attributes domain types, in formative and summative user studies, we investigated how well participants could understand AI decisions from one domain to another. Compared to single-domain and domain-independent explanations, Transferable XAI was the most helpful for understanding the second domain, leading to the best decision faithfulness, factor recall, and ability to relate explanations between domains. This framework contributes to improving the reusability of explanations across related AI applications by explaining factor relationships between subspaces, tasks, and attributes.
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。
