AICLLGMay 8, 2025

Meta-Semantics Augmented Few-Shot Relational Learning

arXiv:2505.05684v41 citationsh-index: 1EMNLP
Originality Incremental advance
AI Analysis

This work addresses the problem of few-shot reasoning on knowledge graphs for AI systems, offering an incremental improvement by leveraging overlooked semantics.

The paper tackles few-shot relational learning on knowledge graphs by proposing PromptMeta, a prompted meta-learning framework that integrates meta-semantics with relational information, achieving effective adaptation to new relations with limited supervision as validated on two real-world benchmarks.

Few-shot relational learning on knowledge graph (KGs) aims to perform reasoning over relations with only a few training examples. While current methods have focused primarily on leveraging specific relational information, rich semantics inherent in KGs have been largely overlooked. To bridge this gap, we propose PromptMeta, a novel prompted meta-learning framework that seamlessly integrates meta-semantics with relational information for few-shot relational learning. PromptMeta introduces two core innovations: (1) a Meta-Semantic Prompt (MSP) pool that learns and consolidates high-level meta-semantics shared across tasks, enabling effective knowledge transfer and adaptation to newly emerging relations; and (2) a learnable fusion mechanism that dynamically combines meta-semantics with task-specific relational information tailored to different few-shot tasks. Both components are optimized jointly with model parameters within a meta-learning framework. Extensive experiments and analyses on two real-world KG benchmarks validate the effectiveness of PromptMeta in adapting to new relations with limited supervision.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes