提出统一的低秩图消息提示方法，同时优化节点、边等所有图组件。
Unified Graph Prompt Learning via Low-Rank Graph Message Prompting
- 将多种图提示方法统一为图消息提示范式，实现统一建模。
- 低秩表示使提示更紧凑，在多个基准数据集上性能超越现有方法。
- 适合需要高效适配预训练图神经网络的研究者使用。
图数据提示（GDP）通过在图数据中引入特定提示，以高效微调预训练图神经网络，已成为主流方法。然而，现有方法分别针对节点特征、边特征、边权重等不同图组件设计，导致提示空间受限。目前尚无能同时作用于所有图组件的统一提示器。本文首次从图消息提示（GMP）视角重新审视多种现有GDP方法，并提出一种新型图提示学习方法——低秩图消息提示（LR-GMP）。该方法利用低秩提示表示，实现高效且紧凑的图提示学习。与传统方法分别处理不同图组件不同，LR-GMP以统一方式同时对所有图组件进行提示，显著提升了在多种下游任务中的泛化性与鲁棒性。在多个图基准数据集上的大量实验验证了其有效性与优势。
原文摘要 · Abstract (English)
Graph Data Prompt (GDP), which introduces specific prompts in graph data for efficiently adapting pre-trained GNNs, has become a mainstream approach to graph fine-tuning learning problem. However, existing GDPs have been respectively designed for distinct graph component (e.g., node features, edge features, edge weights) and thus operate within limited prompt spaces for graph data. To the best of our knowledge, it still lacks a unified prompter suitable for targeting all graph components simultaneously. To address this challenge, in this paper, we first propose to reinterpret a wide range of existing GDPs from an aspect of Graph Message Prompt (GMP) paradigm. Based on GMP, we then introduce a novel graph prompt learning approach, termed Low-Rank GMP (LR-GMP), which leverages low-rank prompt representation to achieve an effective and compact graph prompt learning. Unlike traditional GDPs that target distinct graph components separately, LR-GMP concurrently performs prompting on all graph components in a unified manner, thereby achieving significantly superior generalization and robustness on diverse downstream tasks. Extensive experiments on several graph benchmark datasets demonstrate the effectiveness and advantages of our proposed LR-GMP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。