用任务树统一图数据任务，让GNN学会跨图通用知识。
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
- 构建任务树统一节点、边、图级任务，作为统一学习实例。
- 在30+个图上实现零样本、少样本和微调的强性能。
- 适合做图基础模型研究或跨任务图学习的开发者。
基础模型通过大规模语料预训练，学习图像中的轮廓、纹理、边缘或文本中的词元与句子等跨领域通用模式。然而，在异构图任务中发现此类通用性仍是开放挑战。为此，我们提出一种基于任务树的图跨任务泛化方法，任务树作为统一学习实例，对齐节点、边和图级任务。我们理论分析了任务树的稳定性、可迁移性和泛化能力，表明在多样化的任务树上以重建目标预训练图神经网络（GNN），可生成可迁移知识，从而实现仅需极少微调即可适应下游任务。为验证框架，我们构建了图通用性识别器（GIT），该模型在5个领域的30多个图上，通过微调、上下文学习和零样本泛化均表现出色。代码与数据已公开于https://github.com/Zehong-Wang/GIT。
原文摘要 · Abstract (English)
Foundation models are pretrained on large-scale corpora to learn generalizable patterns across domains and tasks -- such as contours, textures, and edges in images, or tokens and sentences in text. In contrast, discovering such generalities in graph-structured data, especially across heterogeneous graph tasks, remains an open challenge. To address this, we propose a novel approach to cross-task generalization in graphs via task-trees, which serve as unified learning instances aligning node-, edge-, and graph-level tasks. We theoretically analyze the stability, transferability, and generalization properties of task-trees, showing that pretraining a graph neural network (GNN) on diverse task-trees with a reconstruction objective induces transferable knowledge. This enables efficient adaptation to downstream tasks with minimal fine-tuning. To validate our framework, we introduce Graph Generality Identifier on Task-Trees (GIT), a graph foundation model that demonstrates strong performance on over 30 graphs across five domains via fine-tuning, in-context learning, and zero-shot generalization. Code and data are available at https://github.com/Zehong-Wang/GIT.
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。