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 2303.01141cs.LGcs.AI
收藏

DeepSaDe:学习可保证域约束满足的神经网络

DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction

KU Leuven(鲁汶大学);Delft University of Technology(代尔夫特理工大学)

Kshitij Goyal, Sebastijan Dumancic, Hendrik Blockeel

AI总结:

针对现有神经网络约束训练方法无法保证全预测满足约束或约束类型受限的问题,提出DeepSaDe方法,结合层间约束传播与梯度下降+CSP求解的权重更新,实现多类域约束的全预测满足保障。

摘要:

随着机器学习模型(尤其是神经网络)的应用日益广泛,其可信度引发了担忧,在安全关键场景中更是如此,例如自动驾驶车辆的动作必须具备安全性。现有方法可在训练神经网络时将这类域要求作为约束加以实施,但它们要么无法保证所有可能的预测(即使是在未见过的数据上)都满足约束,要么可实施的约束类型存在局限。本文提出了一种训练神经网络的方法,该方法既能实施多种多样的约束,又能保证所有可能的预测都满足约束。该方法以将线性模型学习建模为约束满足问题(CSP)的前期研究为基础,为将这一思路应用于神经网络,引入了两个关键的新要素:网络层间的约束传播,以及结合梯度下降与CSP求解的权重更新机制。在多种机器学习任务上的评估表明,本文方法具备足够的灵活性,能够实施多种多样的域约束,且可在神经网络中保证这些约束得到满足。

英文摘要:

As machine learning models, specifically neural networks, are becoming increasingly popular, there are concerns regarding their trustworthiness, specially in safety-critical applications, e.g. actions of an autonomous vehicle must be safe. There are approaches that can train neural networks where such domain requirements are enforced as constraints, but they either cannot guarantee that the constraint will be satisfied by all possible predictions (even on unseen data) or they are limited in the type of constraints that can be enforced. In this paper, we present an approach to train neural networks which can enforce a wide variety of constraints and guarantee that the constraint is satisfied by all possible predictions. The approach builds on earlier work where learning linear models is formulated as a constraint satisfaction problem (CSP). To make this idea applicable to neural networks, two crucial new elements are added: constraint propagation over the network layers, and weight updates based on a mix of gradient descent and CSP solving. Evaluation on various machine learning tasks demonstrates that our approach is flexible enough to enforce a wide variety of domain constraints and is able to guarantee them in neural networks.

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。

↑