提出路径式解释方法，揭示ReLU网络决策背后的输入关联路径。
Pathwise Explanation of ReLU Neural Networks
- 聚焦决策路径上的隐藏单元子集，替代全网激活状态分析
- 可灵活调整解释粒度，从整体输入到局部特征成分
- 支持解释分解，便于深入理解复杂决策过程
神经网络虽成果丰硕，但其“黑箱”特性引发透明性与可靠性担忧。以往对ReLU网络的研究多基于所有隐藏单元的激活状态，将其解析为线性模型。本文提出一种新方法，关注决策路径中实际参与的隐藏单元子集，实现更清晰、一致的路径级解释。该方法可灵活调整解释范围，从整体输入归因到特定输入组件；同时支持对给定输入的解释进行分解，获得更细粒度的洞察。实验表明，本方法在定量和定性评价上均优于现有方法。
原文摘要 · Abstract (English)
Neural networks have demonstrated a wide range of successes, but their ``black box" nature raises concerns about transparency and reliability. Previous research on ReLU networks has sought to unwrap these networks into linear models based on activation states of all hidden units. In this paper, we introduce a novel approach that considers subsets of the hidden units involved in the decision making path. This pathwise explanation provides a clearer and more consistent understanding of the relationship between the input and the decision-making process. Our method also offers flexibility in adjusting the range of explanations within the input, i.e., from an overall attribution input to particular components within the input. Furthermore, it allows for the decomposition of explanations for a given input for more detailed explanations. Experiments demonstrate that our method outperforms others both quantitatively and qualitatively.
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。