Transfer-and-Fusion: Integrated Link Prediction Across Knowledge Graphs
- 20 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (5) , 3062-3074
Abstract
Existing work on knowledge graph (KG) link prediction has primarily focused on a single KG. However, a single KG is often limited by its incompleteness, encompassing missing facts, entities, and relations. This limitation subsequently restricts the practicality, as it cannot handle the queries that involve missing entities or relations within the single KG. In this paper, we explore an extended link prediction task, cross-KG link prediction, which answers queries using entities or relations integrated from other KGs. The crux of this problem is transferring knowledge across KGs and fusing their embedding spaces, which possess varying schemata. We develop a relation prototype graph to model the interactions among relations from different KGs. Based on this graph, we first propose a dual-view embedding learning module to fuse embedding spaces by training with instance facts and relation prototype edges. We then introduce an attention mechanism to highlight pivotal information for specific queries, recognizing that different KGs often emphasize various domains. Moreover, we devise an augmentation strategy to generate pseudo-cross-KG facts, facilitating knowledge transfer across KGs. Using four widely-used KGs, we construct two cross-KG link prediction datasets. Extensive experimental results demonstrate the superiority of our model and the unique contributions of each module.Keywords
Funding Information
- National Natural Science Foundation of China (62272219, 62406136)
- Collaborative Innovation Center of Novel Software Technology & Industrialization
This publication has 39 references indexed in Scilit:
- Cross-KG Link Prediction by Learning Substructural SemanticsNeural Processing Letters, 2024
- Geometric-Contextual Mutual Infomax Path Aggregation for Relation Reasoning on Knowledge GraphIEEE Transactions on Knowledge and Data Engineering, 2024
- Schema-Aware Hyper-Relational Knowledge Graph Embeddings for Link PredictionIEEE Transactions on Knowledge and Data Engineering, 2023
- AutoAlign: Fully Automatic and Effective Knowledge Graph Alignment Enabled by Large Language ModelsIEEE Transactions on Knowledge and Data Engineering, 2023
- Fast and Slow Thinking: A Two-Step Schema-Aware Approach for Instance Completion in Knowledge GraphsIEEE Transactions on Knowledge and Data Engineering, 2023
- Anytime bottom-up rule learning for large-scale knowledge graph completionThe VLDB Journal, 2023
- Relational Message Passing for Fully Inductive Knowledge Graph Completion2023
- CogKR: Cognitive Graph for Multi-hop Knowledge ReasoningIEEE Transactions on Knowledge and Data Engineering, 2021
- Learning Knowledge Graph Embedding With Heterogeneous Relation Attention NetworksIEEE Transactions on Neural Networks and Learning Systems, 2021
- Knowledge Graph Embedding: A Survey of Approaches and ApplicationsIEEE Transactions on Knowledge and Data Engineering, 2017