SGL-PT：采用图提示调优的强图学习器
SGL-PT: A Strong Graph Learner with Graph Prompt Tuning
AI总结：
针对图预训练与下游任务目标不一致的问题，本文提出 SGL-PT 框架，通过融合生成式与对比式学习的 SGL 预训练任务及无言语化器提示函数统一训练流程，并在无监督和生物数据集上验证其优势。
摘要：
近来，研究者投入大量精力设计图自监督方法，以获得泛化的预训练模型，并通过微调将预训练模型适配到下游任务。然而，预训练图任务与下游图任务之间存在固有差距，这无法充分发挥预训练模型的能力，甚至会导致负迁移。同时，提示调优通过以一致的训练目标对齐预训练与微调，已在自然语言处理中取得新兴成功。本文指出了图提示调优面临的挑战：第一，图领域的各种预训练方法缺乏一个强大且通用的预训练任务；第二，难以为预训练任务和下游任务设计一致的训练目标。为克服上述障碍，我们提出了名为 SGL-PT 的新颖框架，遵循“预训练、提示、预测”的学习策略。具体而言，我们提出了一个强大且通用的预训练任务 SGL，该任务兼具生成式与对比式自监督图学习的互补优势。针对图分类任务，我们通过设计一种新颖的无言语化器提示函数，将下游任务重构为与预训练任务相似的形式，从而统一预训练与微调。实验结果表明，我们的方法在无监督设置下优于其他基线，并且与微调方法相比，我们的提示调优方法能够在生物数据集上显著提升模型性能。
英文摘要：
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.
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。
