提升机器学习解释的效率与紧凑性，兼顾速度与规模。
Efficiently Computing Compact Formal Explanations
- 用边界传播和二分搜索优化解释生成的大小与时间
- 在GTSRB上解释尺寸减少38%，在MNIST上耗时降低90%
- 适用于大模型与真实场景，如自动驾驶与情感分析
基于VeriX（可验证解释系统）提出VeriX+，显著提升形式化解释的紧凑性与生成速度。引入基于边界传播的敏感性分析以减小解释规模，结合基于二分搜索与置信度排序的遍历策略以加速生成，二者相互独立可灵活组合。同时将QuickXplain算法适配至本场景，实现规模与速度的权衡。在标准基准测试中表现优异，例如在GTSRB数据集上解释规模减少38%，在MNIST上生成时间缩短90%。方法可扩展至Transformer模型及真实场景，如自主飞机滑行与情感分析。最后展示了形式化解释的多项新应用。
原文摘要 · Abstract (English)
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.
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。