通过稀疏提示只选关键节点属性，让图模型微调更高效紧凑
Reliable and Compact Graph Fine-tuning via GraphSparse Prompting
- 基于稀疏表示理论，自动筛选关键节点属性进行提示
- 在16个数据集上实现比传统方法更小的提示规模与更高精度
- 适合需要轻量化微调的图神经网络应用场景
近年来，图提示学习在适配预训练图神经网络（GNN）解决下游图学习任务方面受到越来越多关注。然而，现有方法通常对所有图元素（如节点、边、节点属性等）进行提示，存在冗余且非最优。为此，我们引入稀疏表示理论于图提示，提出图稀疏提示（GSP）。GSP旨在自适应地稀疏选择最优元素（如特定节点属性），实现紧凑提示以应对下游任务。具体地，我们设计了两种GSP模型：图稀疏特征提示（GSFP）和图稀疏多特征提示（GSmFP），两者均提供通用框架，可同时实现属性选择与紧凑提示学习，适用于任意预训练GNN。我们还设计了一种简单有效的算法求解该模型。在16个广泛使用的基准数据集上的实验验证了所提方法的有效性与优势。
原文摘要 · Abstract (English)
Recently, graph prompt learning has garnered increasing attention in adapting pre-trained GNN models for downstream graph learning tasks. However, existing works generally conduct prompting over all graph elements (e.g., nodes, edges, node attributes, etc.), which is suboptimal and obviously redundant. To address this issue, we propose exploiting sparse representation theory for graph prompting and present Graph Sparse Prompting (GSP). GSP aims to adaptively and sparsely select the optimal elements (e.g., certain node attributes) to achieve compact prompting for downstream tasks. Specifically, we propose two kinds of GSP models, termed Graph Sparse Feature Prompting (GSFP) and Graph Sparse multi-Feature Prompting (GSmFP). Both GSFP and GSmFP provide a general scheme for tuning any specific pre-trained GNNs that can achieve attribute selection and compact prompt learning simultaneously. A simple yet effective algorithm has been designed for solving GSFP and GSmFP models. Experiments on 16 widely-used benchmark datasets validate the effectiveness and advantages of the proposed GSFPs.
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。