Epistemic uncertainty quantification (UQ) identifies where models lack
knowledge. Traditional UQ methods, often based on Bayesian neural networks, are
not suitable for pre-trained non-Bayesian models. Our study addresses
quantifying epistemic uncertainty for any pre-trained model, which does not
need the original training data or model modifications and can ensure broad
applicability regardless of network architectures or training techniques.
Specifically, we propose a gradient-based approach to assess epistemic
uncertainty, analyzing the gradients of outputs relative to model parameters,
and thereby indicating necessary model adjustments to accurately represent the
inputs. We first explore theoretical guarantees of gradient-based methods for
epistemic UQ, questioning the view that this uncertainty is only calculable
through differences between multiple models. We further improve gradient-driven
UQ by using class-specific weights for integrating gradients and emphasizing
distinct contributions from neural network layers. Additionally, we enhance UQ
accuracy by combining gradient and perturbation methods to refine the
gradients. We evaluate our approach on out-of-distribution detection,
uncertainty calibration, and active learning, demonstrating its superiority
over current state-of-the-art UQ methods for pre-trained models.

我们的研究旨在为任何预训练模型量化认识上的不确定性，不需要原始训练数据或模型修改，可以确保广泛适用于任何网络架构或训练技术；我们提出了一种基于梯度的方法来评估认识上的不确定性，通过分析输出相对于模型参数的梯度，从而指示必要的模型调整以准确地表示输入。

预训练神经网络的认知不确定性量化

Epistemic Uncertainty Quantification For Pre-trained Neural Network

Safe deployment of graph neural networks (GNNs) under distribution shift
requires models to provide accurate confidence indicators (CI). However, while
it is well-known in computer vision that CI quality diminishes under
distribution shift, this behavior remains understudied for GNNs. Hence, we
begin with a case study on CI calibration under controlled structural and
feature distribution shifts and demonstrate that increased expressivity or
model size do not always lead to improved CI performance. Consequently, we
instead advocate for the use of epistemic uncertainty quantification (UQ)
methods to modulate CIs. To this end, we propose G-$\Delta$UQ, a new single
model UQ method that extends the recently proposed stochastic centering
framework to support structured data and partial stochasticity. Evaluated
across covariate, concept, and graph size shifts, G-$\Delta$UQ not only
outperforms several popular UQ methods in obtaining calibrated CIs, but also
outperforms alternatives when CIs are used for generalization gap prediction or
OOD detection. Overall, our work not only introduces a new, flexible GNN UQ
method, but also provides novel insights into GNN CIs on safety-critical tasks.

安全部署图神经网络 (GNNs) 在分布偏移下需要模型提供准确的置信指标 (CI)。然而，尽管众所周知在计算机视觉领域 CI 质量随着分布偏移而降低，但 GNN 领域对此行为的研究仍然不足。因此，我们从在受控的结构和特征分布偏移下进行的 CI 校准案例研究开始，并证明了增强表达能力或模型规模并不总是导致 CI 性能的提高。因此，我们主张使用认识不确定性量化 (UQ) 方法来调节 CI。为此，我们提出了 G-$\Delta$UQ，这是一种新的单模型 UQ 方法，它将最近提出的随机居中框架扩展到支持结构化数据和部分随机性。在协变量、概念和图大小转移方面进行评估，G-$\Delta$UQ 不仅在获取校准 CI 方面优于几种受欢迎的 UQ 方法，而且在使用 CI 进行广义泛化预测或 OOD 检测时也优于其他方法。总的来说，我们的工作不仅引入了一种新的灵活的 GNN UQ 方法，还对安全关键任务中的 GNN CI 提供了新的见解。