---
title: "AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07347v1"
permalink: "https://feed.astralor.com/items/itm_3cec1b4136070168fa927d76"
published: "2026-11-05T02:36:19.000Z"
score: 59
channel: "tech"
tags: ["推理效率","AtlasULP","Domain-aware Universal Link","Prediction","Relation Atlas Link","Conventional","Link","Motivated"]
---

# AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas

## 速览

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 an…

## 关键点

- 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.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_3cec1b4136070168fa927d76