arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.09693cs.LGcs.AI
收藏

神经符号系统的数学框架与一套学习技术

A Mathematical Framework and a Suite of Learning Techniques for Neural-Symbolic Systems

University of California Santa Cruz(加州大学圣克ruz分校);University of Wisconsin Madison(威斯康星大学麦迪逊分校);University of California Santa Barbara(加州大学圣巴巴拉分校)

Charles Dickens, Connor Pryor, Changyu Gao, Alon Albalak, Eriq Augustine, William Wang, Stephen Wright, Lise Getoor

AI总结:

本文提出神经符号能量模型(NeSy-EBMs)统一框架及四种学习方法,并通过NeuPSL库在多个任务中验证其有效性。

摘要:

神经符号(NeSy)系统领域正在迅速发展。所提出的方法在实现神经与符号方法的共生结合方面显示出巨大潜力。然而,需要一个统一的框架来组织常见的NeSy建模模式并开发通用的学习方法。在本文中,我们引入了神经符号能量模型(NeSy-EBMs),这是一个用于判别式和生成式NeSy建模的统一数学框架。重要的是,NeSy-EBMs允许推导主要学习损失梯度的通用表达式,并且我们引入了一套四种学习方法,这些方法利用了多个领域的技术,包括双层和随机策略优化。最后,我们通过神经概率软逻辑(NeuPSL)来落地NeSy-EBM框架,NeuPSL是一个开源的NeSy-EBM库,专为可扩展性和表现力而设计,促进了NeSy系统在实际应用中的部署。通过在多个数据集上的广泛实证分析,我们研究了通过NeuPSL实例化的NeSy-EBMs在图像分类、图节点标注、自动驾驶车辆态势感知和问答等任务中的表现。结果为该实例化在所研究场景中的实际效用提供了证据。

英文摘要:

The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic methods. However, a unifying framework is needed to organize common NeSy modeling patterns and develop general learning approaches. In this paper, we introduce Neural-Symbolic Energy-Based Models (NeSy-EBMs), a unifying mathematical framework for discriminative and generative NeSy modeling. Importantly, NeSy-EBMs allow the derivation of general expressions for gradients of prominent learning losses, and we introduce a suite of four learning approaches that leverage methods from multiple domains, including bilevel and stochastic policy optimization. Finally, we ground the NeSy-EBM framework with Neural Probabilistic Soft Logic (NeuPSL), an open-source NeSy-EBM library designed for scalability and expressivity, facilitating the real-world application of NeSy systems. Through extensive empirical analysis across multiple datasets, we study NeSy-EBMs as instantiated through NeuPSL in tasks including image classification, graph node labeling, autonomous vehicle situation awareness, and question answering. The results provide evidence for the practical utility of this instantiation in the studied settings.

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。

↑