自动发现谱图神经网络传播机制，适配多种图类型。
AutoSGNN: Automatic Propagation Mechanism Discovery for Spectral Graph Neural Networks
- 结合大模型与进化策略，自动搜索最优传播机制。
- 在9个数据集上超越现有方法，在性能与效率上均更优。
- 适合需要快速适配不同图结构的研究者与开发者。
在真实应用中，谱图神经网络（Spectral GNNs）是处理各类图数据的强大工具。然而，单一GNN通常难以同时处理同质图与异质图等不同类型的图。这一挑战促使研究者手工设计针对特定图类型的GNN，但此类方法受限于人力成本和专家知识瓶颈，难以跟上图数据的快速增长。为此，我们提出AutoSGNN，一个自动发现谱图神经网络传播机制的框架。AutoSGNN通过整合大语言模型与进化策略，统一谱图GNN的搜索空间，自动生成可适应多种图类型的架构。在涵盖同质与异质图的9个常用数据集上的大量实验表明，AutoSGNN在性能与效率方面均优于当前最先进的谱图GNN及图神经网络架构搜索方法。
原文摘要 · Abstract (English)
In real-world applications, spectral Graph Neural Networks (GNNs) are powerful tools for processing diverse types of graphs. However, a single GNN often struggles to handle different graph types-such as homogeneous and heterogeneous graphs-simultaneously. This challenge has led to the manual design of GNNs tailored to specific graph types, but these approaches are limited by the high cost of labor and the constraints of expert knowledge, which cannot keep up with the rapid growth of graph data. To overcome these challenges, we propose AutoSGNN, an automated framework for discovering propagation mechanisms in spectral GNNs. AutoSGNN unifies the search space for spectral GNNs by integrating large language models with evolutionary strategies to automatically generate architectures that adapt to various graph types. Extensive experiments on nine widely-used datasets, encompassing both homophilic and heterophilic graphs, demonstrate that AutoSGNN outperforms state-of-the-art spectral GNNs and graph neural architecture search methods in both performance and efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。