Graph neural networks (GNNs) excel in learning from network-like data but often lack interpretability, making their application challenging in domains requiring transparent decision-making. We propose the Graph Kolmogorov-Arnold Network (GKAN), a novel GNN model leveraging spline-based activation functions on edges to enhance both accuracy and interpretability. Our experiments on five benchmark datasets demonstrate that GKAN outperforms state-of-the-art GNN models in node classification, link prediction, and graph classification tasks. In addition to the improved accuracy, GKAN's design inherently provides clear insights into the model's decision-making process, eliminating the need for post-hoc explainability techniques. This paper discusses the methodology, performance, and interpretability of GKAN, highlighting its potential for applications in domains where interpretability is crucial.

翻译：图神经网络（GNNs）在处理网络结构数据方面表现出色，但其可解释性往往不足，这在需要透明决策的领域中应用面临挑战。我们提出了图 Kolmogorov-Arnold 网络（GKAN），这是一种新颖的 GNN 模型，通过在边上采用基于样条的激活函数来同时提升准确性与可解释性。我们在五个基准数据集上的实验表明，GKAN 在节点分类、链接预测和图分类任务中均优于当前最先进的 GNN 模型。除了准确性的提升，GKAN 的设计本身能清晰揭示模型的决策过程，无需依赖事后解释技术。本文讨论了 GKAN 的方法、性能及其可解释性，强调了其在可解释性至关重要的领域中的应用潜力。