arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.21749cs.LG
收藏

基于图稀疏提示的可靠且紧凑的图微调

Reliable and Compact Graph Fine-tuning via GraphSparse Prompting

School of Computer Science and Technology, Anhui University(安徽大学计算机科学与技术学院)

Bo Jiang, Hao Wu, Beibei Wang, Jin Tang, Bin Luo

AI总结:

针对现有图提示学习对全图元素操作存在冗余的问题,提出图稀疏提示方法GSP及两类模型,可自适应稀疏选择最优元素实现紧凑提示,经16个基准数据集验证有效。

摘要:

近年来,图提示学习在适配预训练GNN(图神经网络)模型以用于下游图学习任务方面受到越来越多的关注。然而,现有研究通常对所有图元素(例如节点、边、节点属性等)执行提示操作,这种方式并非最优且存在明显冗余。为解决该问题,我们提出将稀疏表示理论应用于图提示,并提出了Graph Sparse Prompting(GSP,图稀疏提示)方法。GSP旨在自适应地稀疏选择最优元素(例如特定节点属性),为下游任务实现紧凑提示。具体而言,我们提出了两类GSP模型,分别为Graph Sparse Feature Prompting(GSFP,图稀疏特征提示)和Graph Sparse multi-Feature Prompting(GSmFP,图稀疏多特征提示)。GSFP和GSmFP均为调整任意特定预训练GNN提供了通用方案,可同时实现属性选择与紧凑提示学习。我们设计了一种简单有效的算法来求解GSFP和GSmFP模型。在16个广泛使用的基准数据集上的实验验证了所提出的GSFP类方法的有效性与优势。

英文摘要:

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.

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。

↑