arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07738cs.LG
收藏

基于图上上下文学习的通用链接预测器

Universal Link Predictor By In-Context Learning on Graphs

University of Notre Dame(圣母大学);Michigan State University(密歇根州立大学)

Kaiwen Dong, Haitao Mao, Zhichun Guo, Nitesh V. Chawla

AI总结:

提出通用链接预测器UniLP,结合启发式方法的泛化能力与参数化模型的学习能力,通过上下文学习动态适应未见过的图,避免负迁移,性能媲美甚至超越微调模型。

摘要:

链接预测是图机器学习中的一项关键任务,其目标是推断图中缺失或未来的链接。传统方法利用基于广泛观察到的连接模式的启发式方法,在无需模型训练的情况下提供了广泛的适用性和泛化能力。尽管这些方法很实用,但它们受限于对人类推导的启发式规则的依赖,并且缺乏数据驱动方法的适应性。相反,参数化链接预测器擅长从数据中自动学习连接模式并达到最先进的性能,但无法在不同图之间直接迁移。相反,它需要付出大量训练和超参数优化的成本来适应目标图。在这项工作中,我们引入了通用链接预测器(UniLP),这是一种结合了启发式方法的泛化能力与参数化模型模式学习能力的新型模型。UniLP旨在自主识别不同图之间的连接模式,无需针对性训练即可随时应用于任何未见过的图数据集。我们通过实现上下文学习(ICL)来解决由不同图的独特分布引起的冲突连接模式的挑战。这种方法允许UniLP根据上下文演示动态调整到各种目标图,从而避免负迁移。通过严格的实验,我们证明了UniLP在测试时适应新的、未见过的图的有效性,展示了其表现与针对特定数据集微调的参数化模型相当甚至更优的能力。我们的发现突显了UniLP在链接预测中设定新标准的潜力,将启发式和参数化方法的优势结合在一个单一、多功能的框架中。

英文摘要:

Link prediction is a crucial task in graph machine learning, where the goal is to infer missing or future links within a graph. Traditional approaches leverage heuristic methods based on widely observed connectivity patterns, offering broad applicability and generalizability without the need for model training. Despite their utility, these methods are limited by their reliance on human-derived heuristics and lack the adaptability of data-driven approaches. Conversely, parametric link predictors excel in automatically learning the connectivity patterns from data and achieving state-of-the-art but fail short to directly transfer across different graphs. Instead, it requires the cost of extensive training and hyperparameter optimization to adapt to the target graph. In this work, we introduce the Universal Link Predictor (UniLP), a novel model that combines the generalizability of heuristic approaches with the pattern learning capabilities of parametric models. UniLP is designed to autonomously identify connectivity patterns across diverse graphs, ready for immediate application to any unseen graph dataset without targeted training. We address the challenge of conflicting connectivity patterns-arising from the unique distributions of different graphs-through the implementation of In-context Learning (ICL). This approach allows UniLP to dynamically adjust to various target graphs based on contextual demonstrations, thereby avoiding negative transfer. Through rigorous experimentation, we demonstrate UniLP's effectiveness in adapting to new, unseen graphs at test time, showcasing its ability to perform comparably or even outperform parametric models that have been finetuned for specific datasets. Our findings highlight UniLP's potential to set a new standard in link prediction, combining the strengths of heuristic and parametric methods in a single, versatile framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑