让神经网络自己生成简洁可信的预测理由。
Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasons
- 训练模型直接输出预测的最小必要特征子集
- 比传统方法更快更准，且避免异常推理
- 适合需要可解释决策的高风险场景
最小充分理由指使预测结果不变所需的最小输入特征子集。以往后处理方法虽尝试获取此类理由，但存在两大局限：(1) 计算成本高，多数可扩展方法只能收敛到次优、意义不强的子集；(2) 严重依赖分布外样本，可能导致反直觉行为。为此，本文提出自监督训练方法——充分子集训练（SST），使模型在输出预测时同步生成简洁的充分理由。实验表明，该框架比现有后处理方法更高效地生成简洁且忠实的特征子集，同时保持相近的预测性能。
原文摘要 · Abstract (English)
*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.
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。