Analyzing the Impact of Temporal Smoothness Regularisers on Neural Link Prediction in Temporal Knowledge Graphs
Carefully chosen temporal smoothness regularisers can significantly improve the accuracy of neural link prediction in temporal knowledge graphs, with simpler tensor factorization models sometimes outperforming more complex approaches.
Integrating Multi-curvature Shared and Specific Embedding for Temporal Knowledge Graph Completion
The proposed IME model effectively captures the complex geometric structures of temporal knowledge graphs by simultaneously modeling them in multi-curvature spaces, including hyperspherical, hyperbolic, and Euclidean spaces. IME learns both space-shared and space-specific properties to mitigate spatial gaps and comprehensively capture characteristic features across different curvature spaces.
Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space: A Novel Approach
Quaternion embeddings in hypercomplex space enhance temporal knowledge graph completion by capturing time-sensitive relations and periodic patterns.
Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion
Proposing a novel TKGC model, PPT, that leverages pre-trained language models with prompts to effectively incorporate temporal information from knowledge graphs.
Analyzing Temporal Knowledge Graph Completion with Pre-trained Language Models
The author proposes a novel model, PPT, that leverages pre-trained language models and prompts to enhance temporal knowledge graph completion by accurately extracting temporal information and utilizing implied relations. The approach converts the task into a masked token prediction problem.
© 2024 by Linnk AI