研究人员开发了一种名为KMAS的新方法来提高知识图谱基础模型（KGFMs）的性能。该方法通过比传统随机采样更有效地构建“困难负三元组”来增强训练过程。KMAS在训练过程中自适应地调整这些困难负例的比例，以更好地适应KGFM不断发展的能力。在44个数据集上的实验表明，KMAS可以在不显著增加时间或内存的情况下提升最先进的KGFMs。 AI
影响 这项研究为训练知识图谱模型提供了一种更有效的方法，有望提高问答和推荐系统等应用的性能。
排序理由 该集群包含一篇详细介绍改进AI模型新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.27023v1 Announce Type: new Abstract: Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are often very incomplete. To perform zero-shot knowledge graph com…
Knowledge graphs (KGs) have become the core backbone of numerous downstream tasks such as question answering and recommender systems. However, despite all this, KGs are often very incomplete. To perform zero-shot knowledge graph completion in unseen KGs, which have different rela…