发表机构
Florida Atlantic University; University of Louisiana at Lafayette（佛罗里达大西洋大学; 拉斐特路易斯安那大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出SEMGNN，一种端到端自解释多标签图神经网络，联合学习预测器与边掩码解释器，利用标签相关性提升多标签分类性能及解释忠实度，在多类网络上表现优于或相当事后方法。
AI 中文摘要
多标签图学习旨在捕捉真实世界应用的内在复杂性，其中一个样本通常与多个组相关或由多个对象组成。迄今为止，已存在少数多标签图学习方法，但 none 集成了训练时的解释能力。尽管事后图解释器已被开发，但它们未明确建模多标签图学习器中依赖标签的证据共享，尤其是当标签对关联较弱或负相关时。因此，事后方法可能会忽略证据应如何在不同标签间共享或分离。本文提出一种新的端到端自解释多标签图神经网络（SEMGNN），旨在同时对多标签节点进行分类并识别对预测标签有显著贡献的边。与事后方法不同，SEMGNN 在统一框架和训练目标中联合学习预测器和稀疏边掩码解释器。利用标签间相关性改进多标签节点分类并增强单个标签解释，使节点的不同标签可由不同但连贯的结构及/或关联证据支持。在社交网络、娱乐和生命科学领域的合成及真实多标签网络上的实验与比较表明，SEMGNN 实现了具有竞争力或更优的预测性能，同时提供更忠实且紧凑的标签条件解释。
英文摘要
Multi-label graph learning intends to capture the intrinsic complexity of real-world applications, where one sample is often related to multiple groups or consists of multiple objects. To date, a handful of multi-label graph learning methods exist, but none of them integrate training-time interpretation capability. While post-hoc graph explainers have been developed, they do not explicitly model label-dependent evidence sharing in multi-label graph learners, especially when label pairs are weakly or negatively associated. As a result, post-hoc approaches may miss how evidence should be shared or separated across different labels. This paper advances a new end-to-end self-explainable multi-label graph neural network (SEMGNN), which aims to simultaneously classify multi-labeled nodes and identify edges significantly contributing to each target node w.r.t. predicted labels. Different from post-hoc methods, SEMGNN jointly learns a predictor and a sparse edge-mask explainer within a unified framework and training objective. Label-label correlations are used to improve multi-label node classification and enhance individual label explanations, so that different labels of a node can be supported by distinct yet coherent structural and/or correlated evidence. Experiments and comparisons on synthetic and real-world multi-label networks, in social networking, entertainment, and life sciences, show that SEMGNN achieves competitive or improved predictive performance while providing more faithful and compact label-conditioned explanations.
Comments10 pages
