发表机构
Purdue University; Instituto Militar de Engenharia（普渡大学; 军事工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DASH是一种批量方向搜索方法，通过方向Lipschitz界和局部仿射模型生成锚点，快速找到深度网络的有效反事实，在多个数据集上实现高接近性和低延迟。
AI 中文摘要
当反事实解释能够以低延迟生成、保持与事实输入的接近性，并满足输入域、类别和可操作性约束时，它们最为有用。对于深度神经网络而言，同时实现这些目标具有挑战性。启发式方法通常很快，但可能返回无效的反事实，而精确方法可以证明全局接近性，但可能无法在实际时间限制内完成。我们引入了DASH，一种批量启发式搜索方法，用于在$\ell_1$、$\ell_2$和$\ell_\infty$目标下为深度神经网络寻找接近、有效且可操作的反事实。DASH使用方向Lipschitz界和局部仿射模型生成锚点，然后通过批量网络评估对 promising 区域进行排序和扩展。我们将DASH与九种先前的启发式方法以及时间受限的精确混合整数基线在四个表格数据集上进行了比较，网络深度从2到32，并评估了在PBMC3k上的可扩展性。在9,000个表格查询-范数案例中，DASH在94.6%的案例中返回了在最佳启发式观察有效距离的5%以内的有效反事实，中位CPU搜索运行时间为0.061秒。PGD-bisect是池化5%覆盖率最高的基线，在41.1%的案例中达到此标准，中位运行时间为0.298秒。这些结果表明，所提出的搜索方法在各种范数下保持了较高的有效接近性，同时保持了实用的搜索运行时间。
英文摘要
Counterfactual explanations are most useful when they can be generated with low latency, remain close to the factual input, and satisfy input-domain, categorical, and actionability constraints. Achieving these objectives simultaneously is challenging for deep neural networks. Heuristic methods are often fast but may return invalid counterfactuals, whereas exact methods can certify global proximity but may not finish within practical time limits. We introduce DASH, a batched heuristic search method for finding close, valid, and actionable counterfactuals for deep neural networks under $\ell_1$, $\ell_2$, and $\ell_\infty$ objectives. DASH uses directional Lipschitz bounds and local affine models to generate anchors, then ranks and expands promising regions with batched network evaluations. We compare DASH against nine prior heuristic methods and time-limited exact mixed-integer baselines on four tabular datasets, with network depths from 2 to 32, and evaluate scalability on PBMC3k. Across 9,000 tabular query-norm cases, DASH returns a valid counterfactual within $5\%$ of the best heuristic-observed valid distance in $94.6\%$ of cases, with a median CPU search runtime of $0.061$ s. PGD-bisect, the baseline with the highest pooled within-$5\%$ coverage, meets this criterion in $41.1\%$ of cases, with a median runtime of $0.298$ s. These results show that the proposed search maintains high valid proximity across norms while keeping its search runtime practical.
Comments9 pages
