<ul><li>Inductive Knowledge Graph Completion (KGC) aims to infer missing facts between newly emerged entities within knowledge graphs (KGs).</li><li>A Semantic Structure-aware Denoising Network (S^2DN) is proposed for inductive KGC.</li><li>S^2DN addresses the challenges of semantic inconsistencies and noisy interactions in KGs.</li><li>Experimental results show that S^2DN outperforms state-of-the-art models in preserving semantic consistency and filtering out unreliable interactions.</li></ul>

S$^2$DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion

Discover more