Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion
2026-07-03 • Computation and Language
Computation and LanguageArtificial Intelligence
AI summaryⓘ
The authors focus on improving how computers complete missing facts in knowledge graphs from different domains by sharing useful information. Instead of forcing different graphs to be exactly the same for shared entities, which can lose unique details, they use a new method that generates general entity representations using a diffusion-based process informed by related graphs. Their approach balances shared and specific information and works better, especially when there is little data. Tests on multiple datasets show their method improves accuracy compared to previous techniques.
multi-domain knowledge graph completionknowledge transferentity embeddingsdiffusion modelsconditional generationdomain-specific informationtail entity predictionlow-resource learningmean reciprocal rank (MRR)
Authors
Jiawei Sheng, Taoyu Su, Xixun Lin, Xiaodong Li, Tingwen Liu
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.