Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion

2026-07-03

AI Summary

Existing approaches to multi-domain knowledge graph completion struggle to simultaneously achieve effective cross-graph knowledge transfer and preserve entity domain specificity, particularly suffering performance degradation in low-resource settings. To address this challenge, this work proposes DMKGC, a novel generative framework based on conditional diffusion models. DMKGC treats each knowledge graph as a partial view of entities and generates entity embeddings that balance both universality and domain specificity through three key mechanisms: domain-agnostic prior initialization, equivalence-aware entity fusion guidance, and cross-graph predictive training. Evaluated across 14 knowledge graphs spanning three benchmark datasets, the proposed method achieves an average MRR improvement of 4.3% and demonstrates robust superiority even under low-resource conditions.

Abstract

Multi-domain knowledge graph completion (MKGC) aims to improve missing triple prediction in a target KG by transferring knowledge from other support KGs. Existing methods typically enforce consistency constraints on equivalent entities across KGs to transfer knowledge, which risks suppressing domain-specific contextual information of entities. This design can also compromise entity representation information from all KG domains, impeding performance improvements, especially in low-resource data scenarios. To address this, we pioneer a generation-based paradigm for MKGC and propose DMKGC, a conditional diffusion-guided knowledge transfer framework. Our key insight is to treat each KG as a partial view of the entity entire information, and generate informative domain-general entity embeddings through diffusion models conditioned on support KGs. Particularly, we first initialize domain-agnostic entity embeddings as prior entity embeddings, and then encode them within individual KGs. Afterward, we fuse equivalent entities from support KGs as the conditional diffusion generation guidance. We leverage the prior entity embeddings as the proxy generation objective, which ensures this conditional generation to be unbiased towards any conditioned KGs. Simultaneously, we also train the generated embeddings to be predictive across KGs, thus preserving domain-specific information. Extensive experiments on 14 KGs in 3 benchmarks demonstrate a 4.3\% average MRR improvement in tail entity prediction over state-of-the-art methods, with sustained gains in low-resource data settings.

Problem

• Multi-domain Knowledge Graph Completion
• Knowledge Transfer
• Entity Representation
• Low-resource Scenarios
• Domain-specific Information

Innovation

• conditional diffusion
• knowledge transfer
• multi-domain knowledge graph completion
• domain-general embeddings
• generation-based paradigm