Reliable and Compact Graph Fine-tuning via GraphSparse Prompting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Bo, Wu, Hao, Wang, Beibei, Tang, Jin, Luo, Bin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914996784463872
author Jiang, Bo
Wu, Hao
Wang, Beibei
Tang, Jin
Luo, Bin
author_facet Jiang, Bo
Wu, Hao
Wang, Beibei
Tang, Jin
Luo, Bin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21749
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reliable and Compact Graph Fine-tuning via GraphSparse Prompting
Jiang, Bo
Wu, Hao
Wang, Beibei
Tang, Jin
Luo, Bin
Machine Learning
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.
title Reliable and Compact Graph Fine-tuning via GraphSparse Prompting
topic Machine Learning
url https://arxiv.org/abs/2410.21749