arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.02772cs.LG
收藏

双曲基准测试揭示 GNN 性能中的网络拓扑与特征关系

Hyperbolic Benchmarking Unveils Network Topology-Feature Relationship in GNN Performance

Universitat de Barcelona(巴塞罗那大学);UBICS;ICREA(加泰罗尼亚研究与高级研究所)

Roya Aliakbarisani, Robert Jankowski, M. Ángeles Serrano, Marián Boguñá

AI总结:

本研究提出基于双曲空间几何软配置模型的图机器学习基准测试框架,通过生成合成网络评估网络拓扑与节点特征对GNN性能的影响,为模型选择提供指导。

摘要:

图神经网络(GNNs)在预测图属性方面表现优异,应用涵盖社交网络趋势识别、药物发现和恶意软件检测。随着新架构的丰富和复杂性的增加,GNNs 在少数知名数据集上测试时变得高度专业化。然而,GNNs 的性能如何依赖于图的拓扑和特征属性仍是一个开放问题。在本研究中,我们引入了一个全面的图机器学习基准测试框架,重点关注 GNNs 在不同网络结构下的性能。利用双曲空间中的几何软配置模型,我们生成了具有现实拓扑属性和节点特征向量的合成网络。该方法使我们能够评估网络属性(如拓扑-特征相关性、度分布、局部三角形密度(或聚类)和同质性)对不同 GNN 架构有效性的影响。我们的结果突出了模型性能对网络结构与节点特征相互作用的依赖,为各种场景下的模型选择提供了见解。本研究通过提供一个评估 GNNs 的多功能工具,助力基于特定数据特征开发和选择合适模型。

英文摘要:

Graph Neural Networks (GNNs) have excelled in predicting graph properties in various applications ranging from identifying trends in social networks to drug discovery and malware detection. With the abundance of new architectures and increased complexity, GNNs are becoming highly specialized when tested on a few well-known datasets. However, how the performance of GNNs depends on the topological and features properties of graphs is still an open question. In this work, we introduce a comprehensive benchmarking framework for graph machine learning, focusing on the performance of GNNs across varied network structures. Utilizing the geometric soft configuration model in hyperbolic space, we generate synthetic networks with realistic topological properties and node feature vectors. This approach enables us to assess the impact of network properties, such as topology-feature correlation, degree distributions, local density of triangles (or clustering), and homophily, on the effectiveness of different GNN architectures. Our results highlight the dependency of model performance on the interplay between network structure and node features, providing insights for model selection in various scenarios. This study contributes to the field by offering a versatile tool for evaluating GNNs, thereby assisting in developing and selecting suitable models based on specific data characteristics.

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。

↑