用专家混合模型提升少样本关系推理的泛化与适应能力
MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning
- 分离全局共享知识与局部任务上下文，通过专家混合机制学习通用关系原型
- 在三个知识图谱基准上超越现有方法，实现最新性能
- 适合研究少样本学习、知识图谱推理与元学习的科研人员
少样本知识图谱关系学习旨在仅用少量训练样本的情况下对关系进行推理。现有方法虽多采用元学习框架以实现快速适应新关系，但仍存在两大缺陷：一是孤立地学习关系元知识，难以捕捉跨任务的共性关系模式；二是难以有效融入对快速适应至关重要的局部任务上下文。为此，本文提出MoEMeta，一种新型元学习框架，通过解耦全局共享知识与任务特定上下文，实现高效泛化与快速适应。MoEMeta引入两项关键创新：(i) 基于专家混合（MoE）的模型，用于学习全局共享的关系原型以增强泛化能力；(ii) 针对任务定制的适应机制，以捕捉局部上下文实现快速适应。通过平衡全局泛化与局部适应性，MoEMeta显著推进了少样本关系学习。在三个知识图谱基准上的大量实验和分析表明，该方法持续优于现有基线，达到当前最优性能。
原文摘要 · Abstract (English)
Few-shot knowledge graph relational learning seeks to perform reasoning over relations given only a limited number of training examples. While existing approaches largely adopt a meta-learning framework for enabling fast adaptation to new relations, they suffer from two key pitfalls. First, they learn relation meta-knowledge in isolation, failing to capture common relational patterns shared across tasks. Second, they struggle to effectively incorporate local, task-specific contexts crucial for rapid adaptation. To address these limitations, we propose MoEMeta, a novel meta-learning framework that disentangles globally shared knowledge from task-specific contexts to enable both effective model generalization and rapid adaptation. MoEMeta introduces two key innovations: (i) a mixture-of-experts (MoE) model that learns globally shared relational prototypes to enhance generalization, and (ii) a task-tailored adaptation mechanism that captures local contexts for fast task-specific adaptation. By balancing global generalization with local adaptability, MoEMeta significantly advances few-shot relational learning. Extensive experiments and analyses on three KG benchmarks show that MoEMeta consistently outperforms existing baselines, achieving state-of-the-art performance.
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。