简要解释你自己！具有简洁充分理由的自解释神经网络
Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons
AI总结：
针对事后解释方法计算成本高且依赖分布外采样的局限，提出自监督训练方法SST，使模型在输出预测的同时生成简洁充分的解释理由，在保持预测性能的同时显著提升效率与忠实度。
摘要：
*最小充分理由*代表了一种普遍的解释形式——即最小的输入特征子集，当这些特征保持在其对应值不变时，能确保预测结果保持不变。以往的*事后*方法试图获取此类解释，但面临两个主要局限：(1) 获取这些子集构成计算挑战，导致大多数可扩展方法收敛至次优且意义较低的子集；(2) 这些方法严重依赖于对分布外输入赋值的采样，可能引发反直觉行为。为应对这些局限，我们在本工作中提出了一种自监督训练方法，称为*充分子集训练*（SST）。利用SST，我们训练模型为其预测生成简洁的充分理由，并将其作为输出的有机组成部分。结果表明，我们的框架产生简洁且忠实的子集，效率显著优于竞争性事后方法，同时保持相当的预测性能。
英文摘要：
*Minimal sufficient reasons* represent a prevalent form of explanation - the smallest subset of input features which, when held constant at their corresponding values, ensure that the prediction remains unchanged. Previous *post-hoc* methods attempt to obtain such explanations but face two main limitations: (1) Obtaining these subsets poses a computational challenge, leading most scalable methods to converge towards suboptimal, less meaningful subsets; (2) These methods heavily rely on sampling out-of-distribution input assignments, potentially resulting in counterintuitive behaviors. To tackle these limitations, we propose in this work a self-supervised training approach, which we term *sufficient subset training* (SST). Using SST, we train models to generate concise sufficient reasons for their predictions as an integral part of their output. Our results indicate that our framework produces succinct and faithful subsets substantially more efficiently than competing post-hoc methods, while maintaining comparable predictive performance.
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。
