用网络科学分析分类混淆，看清模型学习过程中的真实困惑。
The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning
- 将中间层混淆矩阵转为有向图，用网络科学工具分析分类关系。
- 发现比目鱼与人、男女等类别存在明显混淆，且被人工研究验证。
- 适合关注模型可解释性、训练动态和数据标签问题的研究者。
可解释人工智能已成为应对人工智能可靠性问题的新兴研究方向。尽管该领域取得显著进展，但鲜有方法能系统地可视化和理解类别间的混淆关系及其随训练过程的变化。本文提出GRAPHIC，一种与架构无关的方法，从类别层面分析神经网络。它利用线性分类器在中间层生成的混淆矩阵，将其视为有向图的邻接矩阵，进而运用网络科学工具可视化并量化训练各阶段及中间层的学习动态。GRAPHIC揭示了线性可分性、数据集问题及模型架构行为，例如发现比目鱼与人、男女等类别存在相似性，以及标签模糊性，这些结果经人类研究验证。通过揭示真实混淆现象，GRAPHIC为理解神经网络学习机制提供了新视角。代码已开源：https://github.com/Johanna-S-Froehlich/GRAPHIC。
原文摘要 · Abstract (English)
Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite significant progress in explainable artificial intelligence, few methods provide a systematic way to visualize and understand how classes are confused and how their relationships evolve as training progresses. In this work, we present GRAPHIC, an architecture-agnostic approach that analyzes neural networks on a class level. It leverages confusion matrices derived from intermediate layers using linear classifiers. We interpret these as adjacency matrices of directed graphs, allowing tools from network science to visualize and quantify learning dynamics across training epochs and intermediate layers. GRAPHIC provides insights into linear class separability, dataset issues, and architectural behavior, revealing, for example, similarities between flatfish and man and labeling ambiguities validated in a human study. In summary, by uncovering real confusions, GRAPHIC offers new perspectives on how neural networks learn. The code is available at https://github.com/Johanna-S-Froehlich/GRAPHIC.
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。