学习即漫游：通过随机游走跨图与跨任务学习
To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks
浏览论文内容
中文总结 AI 辅助
提出Wander图基础模型，通过随机游走接口统一处理多种图模态和任务，实现跨图迁移，并在节点分类、链接预测等任务上取得领先性能。
中文摘要 AI 辅助
图基础模型旨在跨图、特征空间、关系模式及预测任务进行迁移，然而现有方法通常仅在特定图模态或任务内泛化。我们提出Wander，一种图基础模型，旨在通过单个预训练检查点在上述各种设置下运行。遵循先验预测视角，我们将图学习形式化为对部分观测图的补全。我们通过基于随机游走的通用接口实现这一任务通用视角，使得同一模型能够处理具有不同特征、标签和关系模式的同质及多关系图。Wander可在推理时增加其结构上下文而无需改变学习参数，并在适当假设下，在连通有界图上通用逼近相应的贝叶斯最优预测器。实验上，单个预训练检查点在节点分类、同质链接预测和知识图谱链接预测上达到最先进或极具竞争力的结果。此外，跨图模态和任务的联合预训练在保持专业设置性能的同时，实现了正迁移和推理时单独学习能力的组合。
英文摘要
Graph foundation models aim to transfer across graphs, feature spaces, relational schemas, and prediction tasks, yet existing approaches typically generalize only within particular graph modalities or tasks. We propose Wander, a graph foundation model designed to operate across these settings within a single pretrained checkpoint. Following the prior-predictive perspective, we formulate graph learning as completion of a partially observed graph. We realize this task-general view through a common interface based on random walks, allowing the same model to operate across homogeneous and multi-relational graphs with varying features, labels, and relational schemas. Wander can increase its structural context at inference time without changing its learned parameters and, under suitable assumptions, universally approximates the corresponding Bayes-optimal predictor on bounded connected graphs. Empirically, a single pretrained checkpoint achieves state-of-the-art or highly competitive results across node classification, homogeneous link prediction, and knowledge-graph link prediction. Moreover, joint pretraining across graph modalities and tasks preserves performance in specialized settings while enabling positive transfer and the composition of separately learned capabilities at inference time.
