用分层高斯过程提升深度网络置信度校准的可解释性
Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks
- 基于网络层级结构设计分层高斯过程，逐层校准预测置信度
- 通过结构化多层核实现全网联合不确定性传播，提升校准一致性
- 适合关注模型可靠性与置信度解释性的研究者使用
校准神经网络分类器的置信度对于评估推理过程中预测的可靠性至关重要。然而，传统高斯过程（GP）校准方法往往无法捕捉深度神经网络内部的层次结构，限制了其可解释性与有效性。本文提出语义感知分层高斯过程（SAL-GP）框架，模拟目标神经网络的分层架构。不同于单一全局GP修正，SAL-GP采用多层GP模型，将每一层的特征表示映射到局部校准修正。各层间通过结构化多层核耦合，实现跨所有层的联合边缘化。该设计能够同时捕捉局部语义依赖与全局校准一致性，并在全网中一致传播预测不确定性。所提框架提升了与网络结构对齐的可解释性，支持对置信度一致性与不确定性量化的严格评估。
原文摘要 · Abstract (English)
Calibrating the confidence of neural network classifiers is essential for quantifying the reliability of their predictions during inference. However, conventional Gaussian Process (GP) calibration methods often fail to capture the internal hierarchical structure of deep neural networks, limiting both interpretability and effectiveness for assessing predictive reliability. We propose a Semantic-Aware Layer-wise Gaussian Process (SAL-GP) framework that mirrors the layered architecture of the target neural network. Instead of applying a single global GP correction, SAL-GP employs a multi-layer GP model, where each layer's feature representation is mapped to a local calibration correction. These layerwise GPs are coupled through a structured multi-layer kernel, enabling joint marginalization across all layers. This design allows SAL-GP to capture both local semantic dependencies and global calibration coherence, while consistently propagating predictive uncertainty through the network. The resulting framework enhances interpretability aligned with the network architecture and enables principled evaluation of confidence consistency and uncertainty quantification in deep models.
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。