基于训练引导的遮挡归因方法，解决特征重要性评估中基线选择的可靠性难题
arXiv:2606.10877v1 Announce Type: new Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturb…
为AI可解释性提出更严谨的特征归因方法，值得关注的研究论文。
arXiv:2604.15898v2 Announce Type: replace Abstract: For around a decade, non-symbolic methods have been the option of choice when explaining complex m…
这项研究证明了在共线性条件下，任何特征排名都无法同时满足忠实性、稳定性和完备性，对机器学习可解释性理论有重要影响。
arXiv:2605.21492v1 Announce Type: cross Abstract: No feature ranking can be simultaneously faithful, stable, and complete when features are collinear.…