Conjugate Relation Modeling for Few-Shot Knowledge Graph Completion

TL;DR

This paper introduces a novel conjugate relation modeling framework for few-shot knowledge graph completion, leveraging advanced encoding, relation learning, and manifold decoding techniques to improve performance on sparse data scenarios.

Contribution

It proposes a comprehensive FKGC framework combining neighborhood aggregation, conjugate relation learning, and manifold decoding, addressing complex relational patterns and data sparsity.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Effectively captures complex relational patterns.

Improves inference efficiency in manifold space.

Abstract

Few-shot Knowledge Graph Completion (FKGC) infers missing triples from limited support samples, tackling long-tail distribution challenges. Existing methods, however, struggle to capture complex relational patterns and mitigate data sparsity. To address these challenges, we propose a novel FKGC framework for conjugate relation modeling (CR-FKGC). Specifically, it employs a neighborhood aggregation encoder to integrate higher-order neighbor information, a conjugate relation learner combining an implicit conditional diffusion relation module with a stable relation module to capture stable semantics and uncertainty offsets, and a manifold conjugate decoder for efficient evaluation and inference of missing triples in manifold space. Experiments on three benchmarks demonstrate that our method achieves superior performance over state-of-the-art methods.