将时序逻辑直接融入深度学习，提升序列任务的准确率与效率
T-ILR: a Neurosymbolic Integration for LTLf
- 基于模糊时序逻辑改进迭代局部优化算法，实现时序约束嵌入
- 在图像序列分类任务中准确率优于现有方法，计算更高效
- 适合需要形式化时序约束的智能系统开发人员使用
当前将符号知识与深度学习结合的方法在静态领域表现良好，但处理时序逻辑规范的研究仍不足。现有方法依赖显式有限状态自动机表示，而本文提出一种新型神经符号框架——时间迭代局部修正（T-ILR），可直接将线性时序逻辑在有限迹上的表达（LTLf）融入序列建模的深度学习架构。该方法扩展了迭代局部修正（ILR）算法，利用近期提出的模糊LTLf解释机制。我们在一个现有的时序神经符号基准上评估T-ILR，该基准包含带有时序知识的图像序列分类任务。实验结果表明，T-ILR在准确率和计算效率方面均优于当前最优方法。
原文摘要 · Abstract (English)
State-of-the-art approaches for integrating symbolic knowledge with deep learning architectures have demonstrated promising results in static domains. However, methods to handle temporal logic specifications remain underexplored. The only existing approach relies on an explicit representation of a finite-state automaton corresponding to the temporal specification. Instead, we aim at proposing a neurosymbolic framework designed to incorporate temporal logic specifications, expressed in Linear Temporal Logic over finite traces (LTLf), directly into deep learning architectures for sequence-based tasks. We extend the Iterative Local Refinement (ILR) neurosymbolic algorithm, leveraging the recent introduction of fuzzy LTLf interpretations. We name this proposed method Temporal Iterative Local Refinement (T-ILR). We assess T-ILR on an existing benchmark for temporal neurosymbolic architectures, consisting of the classification of image sequences in the presence of temporal knowledge. The results demonstrate improved accuracy and computational efficiency compared to the state-of-the-art method.
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。