用逻辑规则提升深度模型对异常数据的识别能力
Improving Out-of-Distribution Detection with Markov Logic Networks
- 引入马尔可夫逻辑网络，通过可解释规则增强检测
- 在多个数据集上显著提升现有检测器性能
- 适合关注模型可解释性与可靠性研究者
开放世界中，深度学习模型的可靠性依赖于异常数据（Out-of-Distribution, OOD）检测。现有方法主要基于统计模型分析神经网络的潜在表示中的异常模式。本文提出将概率推理引入主流OOD检测框架，利用马尔可夫逻辑网络（Markov Logic Networks, MLNs）构建基于人类可理解概念的加权逻辑约束，从而为输入分配概率，提升可解释性。在多个数据集上的大量实验表明，该方法能显著增强多种现有检测器的性能，同时保持计算效率。此外，本文还提出一种从数据中自动学习用于OOD检测的逻辑规则的简单算法，并验证其有效性。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection is essential for ensuring the reliability of deep learning models operating in open-world scenarios. Current OOD detectors mainly rely on statistical models to identify unusual patterns in the latent representations of a deep neural network. This work proposes to augment existing OOD detectors with probabilistic reasoning, utilizing Markov logic networks (MLNs). MLNs connect first-order logic with probabilistic reasoning to assign probabilities to inputs based on weighted logical constraints defined over human-understandable concepts, which offers improved explainability. Through extensive experiments on multiple datasets, we demonstrate that MLNs can significantly enhance the performance of a wide range of existing OOD detectors while maintaining computational efficiency. Furthermore, we introduce a simple algorithm for learning logical constraints for OOD detection from a dataset and showcase its effectiveness.
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。