发现只需半条边就能预测整条关系，揭示知识图谱模型泛化机制
Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Models
- 通过分析半链接（仅头或尾已知）的预测能力，揭示模型泛化路径
- 实证表明：有半链接时模型可准确预测完整三元组，无则性能显著下降
- 为评估和改进知识图谱基础模型提供新诊断框架，适合模型开发者
知识图谱基础模型（KGFMs）具备零样本泛化能力：一次训练即可在未见图谱上预测链接而无需重训。然而，其跨图谱的稳健泛化机制尚不明确。本文深入研究其泛化原理，发现对未见图谱上的链接预测，性能并非均匀分布——尤其当部分链接（称作半链接）可见时表现更优。我们发现，在实际中，仅需观察到测试三元组$(h,r,t)$的半链接$(h,r)$或$(r,t)$之一，模型即可成功预测完整三元组。基于此，我们提出四类组合场景的细粒度分类，并在分层分析中揭示：当前先进模型依赖已见半链接进行预测，而未见半链接带来不同挑战。该分类体系可作为诊断协议，用于评估模型鲁棒性，并指明未来模型改进方向。
原文摘要 · Abstract (English)
Knowledge graph (KG) foundation models (KGFMs) are zero-shot generalizers: trained once, they can predict links on unseen graphs without retraining. However, understanding when and how they can robustly generalize across KGs is still an open question. In this paper, we shed some light on their generalization mechanisms highlighting how their performance on unseen KGs is not uniform when it comes to partially seen links, which we call half-links. In fact, we show that to predict a test triple $(h,r,t)$ it might suffice in practice to have observed the half-link $(h,r)$ or $(r,t)$ in the inference graph. This yields a taxonomy of four scenarios when combinations of these half-links are observed or not. In a rigorous stratified analysis over these scenarios, we reveal that SoTA KGFMs use seen half links for predictions, while unseen half-links pose different challenges. As such, our finer-grained taxonomy can be a diagnostic protocol for robust KGFM generalization and highlights where novel KGFMs can improve.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。