Structure-Aware Zero-Shot Relational Learning for Knowledge Graphs without External Knowledge

Zero-shot Relational Learning (ZRL) aims to perform knowledge graph completion when dealing with newly emerging relations that have no observed triples. However, existing ZRL methods typically rely on external knowledge (e.g., textual descriptions or curated annotations), which increases labeling costs and limits real-world applicability. To overcome this limitation, we propose a new Structure-Aware paradigm for ZRL, termed SAZRL, that performs ZRL without relying on external knowledge. SAZRL leverages intrinsic structural patterns in KGs to bridge semantic correlations for new relations with existing ones. It constructs structure-aware conditional query graphs based on shared entities and adaptive relation updating module to infer representations for new relations based on the query graphs. We conduct extensive experiments on three real-world benchmarks, NELL-ZS, Wiki-ZS and FB15K-ZS, demonstrating that SAZRL consistently surpasses state-of-the-art ZRL methods, achieving up to 10.66% improvement in MRR while eliminating external annotations.