Meta-Semantics Augmented Few-Shot Relational Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Han, Yin, Jie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908628782415872
author Wu, Han
Yin, Jie
author_facet Wu, Han
Yin, Jie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_05684
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta-Semantics Augmented Few-Shot Relational Learning
Wu, Han
Yin, Jie
Artificial Intelligence
Computation and Language
Machine Learning
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.
title Meta-Semantics Augmented Few-Shot Relational Learning
topic Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.05684