MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

TL;DR

MoEMeta introduces a mixture-of-experts meta-learning framework for few-shot relational learning that effectively captures shared relational patterns and local task-specific contexts, leading to improved generalization and rapid adaptation.

Contribution

The paper proposes MoEMeta, a novel meta-learning approach combining mixture-of-experts and task-specific adaptation for few-shot knowledge graph relation learning.

Findings

Achieves state-of-the-art results on three KG benchmarks.

Effectively captures shared relational patterns and local contexts.

Outperforms existing meta-learning baselines.

Abstract

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.