arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.03060cs.LGcs.AI
收藏

高效计算紧凑形式化解释

Efficiently Computing Compact Formal Explanations

Min Wu, Xiaofu Li, Haoze Wu, Clark Barrett

AI总结:

针对现有形式化解释生成系统VeriX的不足,提出VeriX+,通过两项正交优化技术及适配的QuickXplain算法,大幅缩减解释规模与生成时间,可扩展至Transformer及真实场景。

摘要:

基于VeriX(可验证可解释性,arXiv:2212.01051)这一为机器学习模型生成最优可验证解释的系统,我们提出了VeriX+,其在形式化解释的规模和生成时间两方面均实现了显著提升。我们引入基于边界传播的敏感度技术以优化解释规模,同时提出结合置信度排序的基于二分搜索的遍历方法以缩短生成时间——这两项技术相互独立,可单独使用也可组合使用。我们还展示了如何调整QuickXplain算法适配我们的场景,以实现解释规模与生成时间的权衡。在标准基准上的实验评估表明,两项指标均获得显著提升,例如在GTSRB数据集上解释规模缩减38%,在MNIST数据集上生成时间缩减90%。我们验证了该方法可扩展至transformer模型以及飞机自主滑行、情感分析等真实场景,最后展示了形式化解释的若干新颖应用。

英文摘要:

Building on VeriX (Verified eXplainability, arXiv:2212.01051), a system for producing optimal verified explanations for machine learning models, we present VeriX+, which significantly improves both the size and the generation time of formal explanations. We introduce a bound propagation-based sensitivity technique to improve the size, and a binary search-based traversal with confidence ranking for improving time -- the two techniques are orthogonal and can be used independently or together. We also show how to adapt the QuickXplain algorithm to our setting to provide a trade-off between size and time. Experimental evaluations on standard benchmarks demonstrate significant improvements on both metrics, e.g., a size reduction of $38\%$ on the GTSRB dataset and a time reduction of $90\%$ on MNIST. We demonstrate that our approach is scalable to transformers and real-world scenarios such as autonomous aircraft taxiing and sentiment analysis. We conclude by showcasing several novel applications of formal explanations.

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。

↑