# SGL-PT: A Strong Graph Learner with Graph Prompt Tuning

## TL;DR

This paper introduces SGL-PT, a novel graph learning framework that combines strong pre-training with prompt tuning to improve downstream task performance, especially in biological datasets, by bridging the gap between pretext and target tasks.

## Contribution

It proposes a universal pre-training task called SGL and a verbalizer-free prompt tuning method to unify pre-training and downstream tasks in graph learning.

## Key findings

- Outperforms baseline methods in unsupervised settings
- Enhances model performance on biological graph datasets
- Bridges pre-training and fine-tuning gap effectively

## Abstract

Recently, much exertion has been paid to design graph self-supervised methods to obtain generalized pre-trained models, and adapt pre-trained models onto downstream tasks through fine-tuning. However, there exists an inherent gap between pretext and downstream graph tasks, which insufficiently exerts the ability of pre-trained models and even leads to negative transfer. Meanwhile, prompt tuning has seen emerging success in natural language processing by aligning pre-training and fine-tuning with consistent training objectives. In this paper, we identify the challenges for graph prompt tuning: The first is the lack of a strong and universal pre-training task across sundry pre-training methods in graph domain. The second challenge lies in the difficulty of designing a consistent training objective for both pre-training and downstream tasks. To overcome above obstacles, we propose a novel framework named SGL-PT which follows the learning strategy ``Pre-train, Prompt, and Predict''. Specifically, we raise a strong and universal pre-training task coined as SGL that acquires the complementary merits of generative and contrastive self-supervised graph learning. And aiming for graph classification task, we unify pre-training and fine-tuning by designing a novel verbalizer-free prompting function, which reformulates the downstream task in a similar format as pretext task. Empirical results show that our method surpasses other baselines under unsupervised setting, and our prompt tuning method can greatly facilitate models on biological datasets over fine-tuning methods.