Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Conjugate Relation Modeling for Few-Shot Knowledge Graph Completion

Zilong Wang, Qingtian Zeng, Hua Duan, Cheng Cheng, Minghao Zou, Ziyang Wang

TL;DR

A novel FKGC framework for conjugate relation modeling (CR-FKGC) that 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.

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.

Conjugate Relation Modeling for Few-Shot Knowledge Graph Completion

TL;DR

A novel FKGC framework for conjugate relation modeling (CR-FKGC) that 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.

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.
Paper Structure (13 sections, 11 equations, 2 figures, 2 tables)

This paper contains 13 sections, 11 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. method
  3. Neighborhood Aggregation Encoder
  4. Conjugate Relation Learner
  5. Implicit Conditional Diffusion Relation Module
  6. Stable Relation Module
  7. Manifold Conjugate Decoder
  8. EXPERIMENTS
  9. Experimental Setting
  10. Main Results and Analysis
  11. Ablation Study and Parameter Analysis
  12. CONCLUSION
  13. Acknowledgements

Figures (2)

  • Figure 1: The overall framework of CR-FKGC. It consists of three main components: a neighbor aggregation encoder, a conjugate relation learner, and a manifold conjugate decoder.
  • Figure 2: Impact of Diffusion Types and Steps on NELL-One.