AI 中文总结
本文针对图神经网络解释中扰动导致的尺度漂移问题，提出基于噪声扰动的NICE框架，结合随机恢复边界与边界集成梯度提升解释性能与模型忠实度。
AI 中文摘要
事后图神经网络（GNN）解释器通常遵循“扰动-查询”范式，基于对扰动输入的查询预测推断图元素的重要性。然而，此类扰动常引入显著分布偏移，损害用于推导解释的查询预测的可靠性。现有工作主要通过改进扰动图或稳定模型在扰动图上的预测来解决该问题，本文则重新审视扰动机制本身。研究表明，广泛使用的元素级掩码（EM）会将边诱导的消息抑制至零，导致确定性的尺度收缩，该收缩会在消息传递层间累积，本文将此现象称为“尺度漂移”。因此，EM下的预测变化可能混淆信息损坏与传播尺度偏差。作为EM的尺度稳定替代方案，本文引入噪声扰动（NC），通过匹配范数的随机方向扰动每个消息，同时保留期望的消息平方范数。基于NC，本文提出NICE，一种基于噪声扰动的解释框架，该框架在NC诱导的不确定性下学习随机恢复边界（SRB），平衡目标预测恢复与紧凑性。此外，边界集成梯度（BIG）通过沿恢复路径累积每条边对降低恢复风险的贡献，将该边界转换为边属性。在多个基准上的实验表明，所提方法具有更强的解释性能和模型忠实度，同时证实NC大幅降低了掩码诱导的尺度漂移。
英文摘要
Post-hoc Graph Neural Network (GNN) explainers commonly follow a Perturb-Query paradigm, inferring the importance of graph elements based on queried predictions to perturbed inputs. However, such perturbations often introduce substantial distribution shift, undermining the reliability of the queried predictions used to derive explanations. While existing efforts mainly improve perturbed graphs or stabilize model predictions on them, we revisit the perturbation mechanism itself. We show that the widely used Element-wise Masking(EM) suppresses edge-induced messages toward zero, causing deterministic scale contraction that accumulates across message-passing layers, a phenomenon we term Scale Drift. Consequently, prediction changes under EM may conflate information corruption with deviations in propagation scale. As a scale-stable alternative to EM, we introduce Noise Corruption (NC), which perturbs each message through matched-norm random-direction corruption while preserving the expected squared message norm. Building on NC, we propose NICE, a Noise Corruption-based explanation framework, which learns a Stochastic Restoration Boundary (SRB) under NC-induced uncertainty, balancing target-prediction restoration against compactness. Furthermore, Boundary-Integrated Gradient (BIG) converts this boundary into edge attributions by accumulating each edge's contribution to reducing restoration risk along the restoration path. Experiments across multiple benchmarks demonstrate stronger explanation performance and model faithfulness while confirming that NC substantially reduces the Scale Drift induced by masking.
Comments17 pages, 9 figures
