arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.07482cs.LGcs.AI
收藏

面向鲁棒反事实解释的严格概率保证

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations

University of Verona(维罗纳大学);Imperial College London(帝国理工学院)

Luca Marzari, Francesco Leofante, Ferdinando Cicalese, Alessandro Farinelli

AI总结:

针对深度学习模型反事实解释的鲁棒性评估难题,证明合理模型偏移下的鲁棒性计算为NP完全问题,提出带严格概率保证的可扩展方法,在四个二分类数据集上性能优于现有方法。

摘要:

我们研究了深度学习模型反事实解释的鲁棒性评估问题。我们聚焦于改变模型参数的“合理模型偏移(plausible model shifts)”,并提出了一个全新框架来推理该场景下的鲁棒性属性。为论证我们的解决方案,我们首次证明,计算反事实解释相对于合理模型偏移的鲁棒性是NP完全问题。由于这一结论实际上排除了可扩展的精确鲁棒性计算算法的存在可能,我们提出了一种新的概率方法,既能在保证可扩展性的同时,给出具有强理论保证的鲁棒性紧致估计值。值得注意的是,与现有针对合理模型偏移的解决方案不同,我们的方法对被分析的网络没有特殊要求,因此可支持更广泛架构的鲁棒性分析。在四个二分类数据集上的实验表明,我们的方法在生成鲁棒解释方面提升了当前最优水平,在多项指标上均优于现有方法。

英文摘要:

We study the problem of assessing the robustness of counterfactual explanations for deep learning models. We focus on $\textit{plausible model shifts}$ altering model parameters and propose a novel framework to reason about the robustness property in this setting. To motivate our solution, we begin by showing for the first time that computing the robustness of counterfactuals with respect to plausible model shifts is NP-complete. As this (practically) rules out the existence of scalable algorithms for exactly computing robustness, we propose a novel probabilistic approach which is able to provide tight estimates of robustness with strong guarantees while preserving scalability. Remarkably, and differently from existing solutions targeting plausible model shifts, our approach does not impose requirements on the network to be analyzed, thus enabling robustness analysis on a wider range of architectures. Experiments on four binary classification datasets indicate that our method improves the state of the art in generating robust explanations, outperforming existing methods on a range of metrics.

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。

↑