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 2501.08281cs.LG
收藏

NEUROLOGIC:从神经表征到可解释逻辑规则

NEUROLOGIC: From Neural Representations to Interpretable Logic Rules

Chuqin Geng, Anqi Xing, Li Zhang, Ziyu Zhao, Yuhe Jiang, Xujie Si

AI总结:

NEUROLOGIC提出从深度神经网络任意层神经表征直接提取可解释逻辑规则的新框架,支持丰富逻辑结构与人类先验知识,在Transformer情感分析上验证了有效性与可扩展性。

摘要:

基于规则的解释方法为神经网络行为提供了严谨且全局可解释的洞见。然而,现有方法大多局限于小型全连接网络,并依赖于代价高昂的逐层规则提取与替换过程。这些局限性阻碍了其向更复杂架构(如Transformer)的泛化。此外,现有方法产生浅层的、类似决策树的规则,无法捕捉计算机视觉和自然语言处理等复杂领域中的丰富高层抽象。为应对这些挑战,我们提出了NEUROLOGIC,一种新颖的框架,可直接从深度神经网络中提取可解释的逻辑规则。与以往方法不同,NEUROLOGIC能够在任意选定层上基于神经表征所导出的隐藏谓词构建逻辑规则,而无需代价高昂的逐层提取与重写。这种灵活性使其具有更广泛的架构兼容性和更高的可扩展性。此外,NEUROLOGIC支持更丰富的逻辑结构,并能融合人类先验知识,将隐藏谓词锚定回输入空间,从而增强可解释性。我们在基于Transformer的情感分析任务上验证了NEUROLOGIC,展示了其提取有意义、可解释的逻辑规则并提供更深层洞见的能力——而现有方法在这些任务上难以扩展。

英文摘要:

Rule-based explanation methods offer rigorous and globally interpretable insights into neural network behavior. However, existing approaches are mostly limited to small fully connected networks and depend on costly layerwise rule extraction and substitution processes. These limitations hinder their generalization to more complex architectures such as Transformers. Moreover, existing methods produce shallow, decision-tree-like rules that fail to capture rich, high-level abstractions in complex domains like computer vision and natural language processing. To address these challenges, we propose NEUROLOGIC, a novel framework that extracts interpretable logical rules directly from deep neural networks. Unlike previous methods, NEUROLOGIC can construct logic rules over hidden predicates derived from neural representations at any chosen layer, in contrast to costly layerwise extraction and rewriting. This flexibility enables broader architectural compatibility and improved scalability. Furthermore, NEUROLOGIC supports richer logical constructs and can incorporate human prior knowledge to ground hidden predicates back to the input space, enhancing interpretability. We validate NEUROLOGIC on Transformer-based sentiment analysis, demonstrating its ability to extract meaningful, interpretable logic rules and provide deeper insights-tasks where existing methods struggle to scale.

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。

↑