AtlasULP：基于关系图谱的领域感知通用链接预测框架
AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas
一篇图学习论文，提出 AtlasULP 框架，在没见过的图上不用重新训练就能做链接预测，生物网络这类长程依赖场景提升明显，做图方向的朋友可以看看。
链接预测（LP）传统上需要对每个图数据集单独训练模型，成本高且难以复用。arXiv 论文 AtlasULP 提出关系图谱（relation atlas）表示，从全局和局部两个视角捕捉节点对之间的结构关联，以支持在未见过的图上免训练推理。相比依赖子图采样的现有 ULP 方法，它能保留高阶邻域的长程信号，在生物网络等场景中表现更好。模型还通过领域引导的提示词机制生成领域感知 prompt token，实现自适应的上下文内链接推断。实验显示 AtlasULP 在多个图领域上均超过现有 SOTA 方法。
AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas
Link prediction (LP) is a widely applied task in graph learning. Conventional LP approaches typically follow a dataset-specific paradigm, requiring independent training for each graph and incurring high computational and maintenance costs in large-scale applications. Motivated by these limitations, recent work explores Universal Link Prediction (ULP), aiming to enable training-free inference on arbitrary unseen graphs. However, existing methods primarily rely on subgraph sampling strategies to construct universal representations, which are unable to capture higher-order information due to the exponential growth of higher-order neighborhoods. As a result, they often under-perform on graphs where long-range signals are essential, such as biological networks. Moreover, their prediction models are typically domain-agnostic and lack the ability to adapt to different graph domains, leading to limited generalization. To address these challenges, we propose an Atlas-based Universal Link Prediction framework (AtlasULP), which introduces the relation atlas to capture structural associations between node pairs from both global and local perspectives, enabling a comprehensive characterization of connectivity signals across diverse graph domains. Building upon this representation, we develop a domain-guided prompting ULP model, which generates domain-aware prompt tokens from contextual structures and performs prompt-guided in-context prediction for adaptive link inference. Extensive experiments demonstrate that AtlasULP consistently outperforms state-of-the-art methods across diverse graph domains.