Meta-Semantics Augmented Few-Shot Relational Learning
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.