发表机构
Google Research; Google DeepMind（谷歌研究院; 谷歌DeepMind）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出通用分类器（UC），通过将异构特征和标签提升为3D潜在张量并统一基于相似性的分类目标，实现跨节点、边和图级任务的零样本迁移，支持任意特征和类别基数。
AI 中文摘要
虽然基础模型通过利用通用词汇彻底改变了自然语言处理和计算机视觉，但图机器学习（GML）由于缺乏跨不同领域的统一特征和结构表示而仍然处于分裂状态。现有声称是图基础模型（GFMs）的工作通常局限于节点级预测或需要固定的特征维度，未能为图学习应用的完整范围提供真正任务无关的骨干。在本文中，我们引入了通用分类器（UC），它支持任意特征和类别基数，将节点级、边级和图级目标统一在基于相似性的单一分类目标下。UC将所有节点级、边级和图级预测任务重新表述为在潜在空间中最大化相似性：通过将异构特征和标签提升为3D潜在张量，模型学习独立于特定输入模式的迁移特征。这种架构允许单个预训练模型泛化到跨未见图（具有不同特征语义）的节点分类、节点回归和链接预测。实验表明，在节点级、链接级和图级任务上具有强大的零样本迁移性能。
英文摘要
While foundation models have revolutionized natural language processing and computer vision by leveraging universal vocabularies, Graph Machine Learning (GML) remains fractured due to the absence of a unified feature and structural representation across diverse domains. Existing works claiming to be Graph Foundation Models (GFMs) are typically restricted to node-level predictions or require fixed feature dimensions, failing to provide a truly task-agnostic backbone for the full spectrum of graph learning applications. In this paper, we introduce the Universal Classifier (UC), which supports arbitrary feature and class cardinalities, unifying node-, edge-, and graph-level objectives under a single similarity-based classification objective. The UC reformulates all node-, edge-, and graph-level prediction tasks as maximizing similarity in the latent space: by lifting heterogeneous features and labels into 3D latent tensors, the model learns transferable features independent of specific input schemas. This architecture allows a single pre-trained model to generalize to node classification, node regression, and link prediction across unseen graphs with varying feature semantics. Experiments show strong zero-shot transfer performance across node-, link-, and graph-level tasks.
