将宽深学习引入图分类，提升模型在节点特征与结构间的平衡能力。
Wide & Deep Learning for Node Classification
- 融合宽深架构，结合记忆与泛化能力提升性能
- 在半监督与全监督任务中均减少过拟合与过泛化
- 支持大模型辅助特征工程，适用于跨域节点分类
广义线性模型的记忆能力与深度模型的泛化能力结合的宽深学习架构（Wide & Deep）在推荐系统中取得显著成功。尽管图卷积网络（GCNs）仍是节点分类主流方法，但其对异质性与表达力的关注不足，常忽略节点特征的作用。本文提出灵活框架GCNIII，引入交集记忆、初始残差与身份映射三项技术，基于宽深架构实现更优的过拟合与过泛化权衡。实验表明，GCNIII在多种半监督和全监督任务中表现稳健。此外，我们探索使用大语言模型（LLMs）进行节点特征工程，显著提升跨域节点分类性能。代码已开源：https://github.com/CYCUCAS/GCNIII。
原文摘要 · Abstract (English)
Wide & Deep, a simple yet effective learning architecture for recommendation systems developed by Google, has had a significant impact in both academia and industry due to its combination of the memorization ability of generalized linear models and the generalization ability of deep models. Graph convolutional networks (GCNs) remain dominant in node classification tasks; however, recent studies have highlighted issues such as heterophily and expressiveness, which focus on graph structure while seemingly neglecting the potential role of node features. In this paper, we propose a flexible framework GCNIII, which leverages the Wide & Deep architecture and incorporates three techniques: Intersect memory, Initial residual and Identity mapping. We provide comprehensive empirical evidence showing that GCNIII can more effectively balance the trade-off between over-fitting and over-generalization on various semi- and full- supervised tasks. Additionally, we explore the use of large language models (LLMs) for node feature engineering to enhance the performance of GCNIII in cross-domain node classification tasks. Our implementation is available at https://github.com/CYCUCAS/GCNIII.
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。