arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.04892cs.AIcs.LG
收藏

基于加权模型积分的概率机器学习验证

Probabilistic ML Verification via Weighted Model Integration

University of Trento(特伦托大学);DISI(信息工程与计算机科学系)

Paolo Morettin, Andrea Passerini, Roberto Sebastiani

AI总结:

本文提出基于加权模型积分(WMI)的统一框架,将机器学习模型的概率形式化验证归约为 WMI,从而在广泛系统上验证公平性、单调性、鲁棒性和等价性等多种性质,并推广了现有可扩展性技术。

摘要:

在机器学习(ML)验证中,大多数方法是非定量的,因此无法用于验证概率模型,也无法应用于实际上难以获得硬性保证的领域。机器学习模型的概率形式化验证(PFV)仍处于起步阶段,现有方法仅限于特定的机器学习模型、特定的性质,或两者兼有。这与标准形式化方法技术形成鲜明对比,后者在现实场景中的成功应用也得益于其对广泛性质和多样系统的支持。我们提出了一个基于加权模型积分(Weighted Model Integration, WMI)的机器学习系统概率形式化验证统一框架;WMI 是一种相对较新的形式化方法,用于带代数约束和逻辑约束的概率推理。关键在于,将机器学习模型的概率形式化验证归约为 WMI,能够在广泛的系统上验证众多感兴趣的性质,从而解决确定性验证和专用算法的多重局限。我们在若干原型任务上证实了该方法的通用性,这些任务涉及群体公平性、单调性、噪声鲁棒性、概率局部鲁棒性以及预测器之间等价性的验证。我们刻画了与该方法可扩展性相关的挑战,并基于 WMI 视角展示了机器学习验证文献中成功的扩展技术如何能够被推广到其原始适用范围之外。

英文摘要:

In machine learning (ML) verification, the majority of procedures are non-quantitative and therefore cannot be used for verifying probabilistic models, or be applied in domains where hard guarantees are practically unachievable. The probabilistic formal verification (PFV) of ML models is in its infancy, with the existing approaches limited to specific ML models, properties, or both. This contrasts with standard formal methods techniques, whose successful adoption in real-world scenarios is also due to their support for a wide range of properties and diverse systems. We propose a unifying framework for the PFV of ML systems based on Weighted Model Integration (WMI), a relatively recent formalism for probabilistic inference with algebraic and logical constraints. Crucially, reducing the PFV of ML models to WMI enables the verification of many properties of interest over a wide range of systems, addressing multiple limitations of deterministic verification and ad-hoc algorithms. We substantiate the generality of the approach on prototypical tasks involving the verification of group fairness, monotonicity, robustness to noise, probabilistic local robustness and equivalence among predictors. We characterize the challenges related to the scalability of the approach and, through our WMI-based perspective, we show how successful scaling techniques in the ML verification literature can be generalized beyond their original scope.

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。

↑