归因解释的向后兼容性及增强模型训练方法
Backward Compatibility in Attributive Explanation and Enhanced Model Training Method
AI总结:
本文针对模型更新导致特征归因解释不一致的问题,提出 BCX 兼容性指标及带代理损失的 BCXR 训练方法,并在八个数据集上验证其能更好权衡预测性能与解释稳定性。
摘要:
模型更新是 ML/AI 系统运行中的关键过程。虽然更新模型通常会提升平均预测性能,但也会显著影响预测解释。在实际应用中,即使解释发生微小变化,也可能造成有害后果。为解决这一问题,本文提出 BCX,这是一种定量指标,用于评估更新前与更新后模型之间特征归因解释的向后兼容性。BCX 利用实用的一致性指标来计算更新前与更新后模型解释之间的平均一致性,具体针对两个模型都能准确预测的样本。此外,我们提出 BCXR,这是一种感知 BCX 的模型训练方法,通过设计代理损失从理论上为一致性分数提供下界。进一步地,我们提出 BCXR 的通用变体,利用模型解释之间的 L2 距离来改进所有一致性指标。为验证该方法,我们在八个真实世界数据集上进行了实验,结果表明 BCXR 在预测性能与 BCX 分数之间实现了更优的权衡,展示了 BCXR 方法的有效性。
英文摘要:
Model update is a crucial process in the operation of ML/AI systems. While updating a model generally enhances the average prediction performance, it also significantly impacts the explanations of predictions. In real-world applications, even minor changes in explanations can have detrimental consequences. To tackle this issue, this paper introduces BCX, a quantitative metric that evaluates the backward compatibility of feature attribution explanations between pre- and post-update models. BCX utilizes practical agreement metrics to calculate the average agreement between the explanations of pre- and post-update models, specifically among samples on which both models accurately predict. In addition, we propose BCXR, a BCX-aware model training method by designing surrogate losses which theoretically lower bounds agreement scores. Furthermore, we present a universal variant of BCXR that improves all agreement metrics, utilizing L2 distance among the explanations of the models. To validate our approach, we conducted experiments on eight real-world datasets, demonstrating that BCXR achieves superior trade-offs between predictive performances and BCX scores, showcasing the effectiveness of our BCXR methods.
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。