A Unified Graph Selective Prompt Learning for Graph Neural Networks

TL;DR

This paper introduces a unified graph prompt learning method for GNNs that selectively focuses on important nodes and edges, improving adaptation to downstream tasks while addressing limitations of previous prompt learning approaches.

Contribution

It proposes a novel GSPF method that integrates node and edge prompts and selectively learns prompts on key graph components, enhancing robustness and efficiency.

Findings

Outperforms existing prompt learning methods on benchmark datasets.

Effectively captures important nodes and edges for better task alignment.

Demonstrates robustness against noisy graph data.

Abstract

In recent years, graph prompt learning/tuning has garnered increasing attention in adapting pre-trained models for graph representation learning. As a kind of universal graph prompt learning method, Graph Prompt Feature (GPF) has achieved remarkable success in adapting pre-trained models for Graph Neural Networks (GNNs). By fixing the parameters of a pre-trained GNN model, the aim of GPF is to modify the input graph data by adding some (learnable) prompt vectors into graph node features to better align with the downstream tasks on the smaller dataset. However, existing GPFs generally suffer from two main limitations. First, GPFs generally focus on node prompt learning which ignore the prompting for graph edges. Second, existing GPFs generally conduct the prompt learning on all nodes equally which fails to capture the importances of different nodes and may perform sensitively w.r.t noisy nodes in aligning with the downstream tasks. To address these issues, in this paper, we propose a new unified Graph Selective Prompt Feature learning (GSPF) for GNN fine-tuning. The proposed GSPF integrates the prompt learning on both graph node and edge together, which thus provides a unified prompt model for the graph data. Moreover, it conducts prompt learning selectively on nodes and edges by concentrating on the important nodes and edges for prompting which thus make our model be more reliable and compact. Experimental results on many benchmark datasets demonstrate the effectiveness and advantages of the proposed GSPF method.