arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.00753cs.LGcs.AI
收藏

图神经网络K--图分类与可解释性

GraphNNK -- Graph Classification and Interpretability

Faculty of Electrical Engineering University of Montenegro(电气工程学院南斯拉夫蒙特内格罗大学)

Zeljko Bolevic, Milos Brajovic, Isidora Stankovic, Ljubisa Stankovic

AI总结:

图神经网络K通过非负核回归方法提升图分类的可解释性与泛化能力。

摘要:

图神经网络(GNNs)已成为从图结构数据中学习的标准方法。然而,其依赖于参数化分类器(通常为线性softmax层)限制了可解释性,并且有时会阻碍泛化能力。最近基于插值的方法,特别是非负核回归(NNK),已证明预测可以表示为嵌入空间中相似训练示例的凸组合,从而获得理论结果和可解释的解释。

英文摘要:

Graph Neural Networks (GNNs) have become a standard approach for learning from graph-structured data. However, their reliance on parametric classifiers (most often linear softmax layers) limits interpretability and sometimes hinders generalization. Recent work on interpolation-based methods, particularly Non-Negative Kernel regression (NNK), has demonstrated that predictions can be expressed as convex combinations of similar training examples in the embedding space, yielding both theoretical results and interpretable explanations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑