从人眼视觉系统出发，揭示神经网络偏见的几何成因。
Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective
- 通过类感知流形的几何复杂度分析偏见来源
- 发现不同类别几何复杂度差异导致识别能力不均
- 适合研究公平性与模型可解释性的学者
深度神经网络（DNN）中的偏见问题仍是关键但未被充分理解的挑战，影响人工智能系统的公平性与可靠性。受人类视觉系统通过分层处理解耦物体流形以实现物体识别的启发，本文提出一种几何分析框架，将DNN中类别特异性感知流形的几何复杂度与模型偏见关联起来。研究发现，几何复杂度的差异会导致不同类别间识别能力不一致，从而引入偏见。为支持该分析，我们构建了感知流形几何工具库（Perceptual-Manifold-Geometry library），用于计算感知流形的几何属性。该工具包已下载安装超过4,500次。本工作为现代学习系统中的偏见形成提供了新颖的几何视角，并为构建更公平、更鲁棒的人工智能奠定了理论基础。
原文摘要 · Abstract (English)
Bias formation in deep neural networks (DNNs) remains a critical yet poorly understood challenge, influencing both fairness and reliability in artificial intelligence systems. Inspired by the human visual system, which decouples object manifolds through hierarchical processing to achieve object recognition, we propose a geometric analysis framework linking the geometric complexity of class-specific perceptual manifolds in DNNs to model bias. Our findings reveal that differences in geometric complexity can lead to varying recognition capabilities across categories, introducing biases. To support this analysis, we present the Perceptual-Manifold-Geometry library, designed for calculating the geometric properties of perceptual manifolds. The toolkit has been downloaded and installed over 4,500 times. This work provides a novel geometric perspective on bias formation in modern learning systems and lays a theoretical foundation for developing more equitable and robust artificial intelligence.
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。