发表机构
School of Computer Science and Cyber Engineering, Guangzhou University; Hunan University of Technology and Business（广州大学计算机科学与网络工程学院; 湖南工商大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对多任务图预训练中提示空间与结构特征对齐差的问题，提出双先验提示初始化方案TPGC，在6个主流基准的少样本设置下性能优于现有方法。
AI 中文摘要
图提示学习是一种在低资源场景下将预训练图模型适配到下游任务的有效范式。然而，现有的多任务图预训练框架通常使用随机初始化的提示，导致提示空间、预训练目标与图结构特征之间的对齐效果较差，这极大削弱了提示表示的任务相关性、结构感知能力和可迁移性。为解决这一挑战，我们提出TPGC，一种双先验提示初始化方案，明确建模任务先验与结构先验之间的协同作用。具体而言，任务先验注入模块首先在辅助图上进行短时长的同源多任务预训练，使提示初始化继承与多个预文本任务相关的优化偏好。基于任务感知表示，结构先验注入模块进一步从辅助图中提取可迁移的全局结构上下文，通过聚合具有结构信息的节点嵌入将其转换为分层提示向量。在涵盖节点分类和图分类的6个主流基准上开展的大量实验表明，TPGC在少样本设置下比现有最先进基线实现了始终更优的性能，同时具有更少的下游可调参数和更低的运行时间。代码可在指定URL获取。
英文摘要
Graph prompt learning is an effective paradigm to adapt pre-trained graph models to downstream tasks in low-resource scenarios. However, existing multi-task graph pre-training frameworks generally use randomly initialized prompts, leading to poor alignment between the prompt space, pretext objectives and graph structural characteristics. This greatly weakens the task relevance, structural awareness and transferability of prompt representations. To address this challenge, we propose TPGC, a dual-prior prompt initialization solution that explicitly models the synergy between task prior and structural prior. Specifically, the Task-Prior Injection Module first conducts a short homologous multi-task pre-training on an auxiliary graph, enabling prompt initialization to inherit optimization preferences associated with multiple pretext tasks. Built on the task-aware representations, the Structure-Prior Injection Module further extracts transferable global structural context from the auxiliary graph, converting it into layer-wise prompt vectors by aggregating structurally informative node embeddings. Extensive experiments on 6 mainstream benchmarks covering node and graph classification show that TPGC achieves consistently better performance under few-shot settings than state-of-the-art baselines, with fewer downstream tunable parameters and lower runtime. The code is available at https://github.com/Virgilqiu/TPGC
Comments16 pages, 6 figures
