提出可扩展验证的神经可解释推理框架，让深度学习模型既强大又透明。
Neural Interpretable Reasoning
- 将可解释性视为马尔可夫性质，结合神经重参数化降低验证复杂度
- 构建生成与可解释执行并行的新范式，支持大规模等变性验证
- 适合需要高透明度的AI系统，如医疗诊断、金融决策
我们提出一种新的建模框架，以实现深度学习中的可解释性，其核心是推理等变性原则。尽管直接验证可解释性的复杂度随系统变量数量呈指数增长，但通过将可解释性视为马尔可夫性质，并利用神经重参数化技术，可有效缓解这一问题。基于此，我们提出一种新范式——神经生成与可解释执行，该范式支持等变性的大规模可验证性。该方法为设计兼具表达力与透明性的神经可解释推理器提供通用路径。
原文摘要 · Abstract (English)
We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of variables of the system, we show that this complexity can be mitigated by treating interpretability as a Markovian property and employing neural re-parametrization techniques. Building on these insights, we propose a new modeling paradigm -- neural generation and interpretable execution -- that enables scalable verification of equivariance. This paradigm provides a general approach for designing Neural Interpretable Reasoners that are not only expressive but also transparent.
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。