arXiv 2406.183542025-05-30cs.LGcs.AI

Kolmogorov-Arnold图神经网络

Kolmogorov-Arnold Graph Neural Networks

Department of Computer, Control and Management Engineering, Sapienza University of Rome（西帕辛扎大学罗马分校计算机、控制与管理工程系）；Department of Life Science Informatics and Data Science, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universität, Bonn, Germany（波恩德国莱茵-威斯巴登大学生命科学信息技术与数据科学系）；Lamarr Institute for Machine Learning and Artificial Intelligence, Bonn, Germany（波恩德国拉马尔机器学习与人工智能研究所）

Gianluca De Carlo, Andrea Mastropietro, Aris Anagnostopoulos

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出GKAN模型，通过边上的样条激活函数提升GNN的准确性与可解释性，在五类基准数据集上优于现有模型，无需事后解释技术。

摘要：

图神经网络（GNNs）擅长从网络状数据中学习，但往往缺乏可解释性，使其在需要透明决策的领域中应用具有挑战性。我们提出了Graph Kolmogorov-Arnold Network（GKAN），这是一种新型GNN模型，利用边上的基于样条的激活函数来同时增强准确性和可解释性。我们在五个基准数据集上的实验表明，GKAN在节点分类、链路预测和图分类任务中优于最先进的GNN模型。除了准确性的提升，GKAN的设计本质上为模型的决策过程提供了清晰的洞察，消除了对事后可解释性技术的需求。本文讨论了GKAN的方法论、性能和可解释性，强调了其在可解释性至关重要的领域中的应用潜力。

英文摘要：

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.

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。