.png){kind=icon}
Return
Decentralised Knowledge Graph Evolution via Blockchain
.png){kind=icon}
PRE
AI
DOI：10.1109/TSC.2023.3337873.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In recent years, knowledge graphs (KGs) have been applied in various domains, where the construction and maintenance of the KGs are usually time- and labor-intensive. In this context, constructing shareable KG through multiple constructors is being attempted to reduce costs. In this collaborative process, security and quality issues are critical. The system for constructing shareable KGs should be capable to recover the KG from most malicious attack and to filter out wrong triples from dynamically submitted ones. Blockchain could naturally prevent malicious tampering with its record data, perfect for solving the security issue. However, the integration of multi-source KGs as well as the quality issue still lacks solutions. To address the issues, this paper proposes a blockchain-based high-quality KG collaborative construction framework to ensure the KG quality in its long-term evolution. The framework is built on the underlying consensus mechanism of the blockchain, adopted to an extensible data structure to store multi-source triples on the distributed ledger. A smart contract is implemented to publish triples, assess the contributor credibility and evaluate triple quality to keep the KG in high-quality. Anti-attack mechanisms are designed to defend against malicious triple submissions. Experiments are conducted demonstrating the effectiveness of the framework.
Keywords:
Blockchain
knowledge graph
knowledge management
knowledge quality
multi-contributors
Journal
IF:
5.8
Papers:
2.2K
Citations:
6.5K
Organization
Cited Papers
Tissue specific and developmental expression of isozymes in barley (Hordeurn vulgare L.).png)
Hereditas
OAAI
HereditasIF0
OAAIShareSaveExploring adaptation strategies of coffee production to climate change using a process-based model
PREAI
ShareSaveShareSaveShareSaveShareSaveShareSave
View more