Multi-task learning approaches for knowledge graph completion, such as MT-DNN and LP-BERT, fail to resolve the fundamental scalability gap in large-scale knowledge graphs, where latency grows polynomially with graph density.

Authors

• Person: Not available Organization: Frontiers
  Practices, opportunities and challenges in the fusion of knowledge ...

Sources

• Practices, opportunities and challenges in the fusion of knowledge ... www.frontiersin.org Frontiers via serper

Referenced by nodes (5)

• knowledge graphs concept
• Knowledge Graph completion concept
• scalability concept
• latency concept
• multi-task learning concept