Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
TransERR is a translation-based knowledge graph embedding model that utilizes efficient relation rotation in the hypercomplex-valued space to enhance translation freedom and capture latent information between entities.
TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
TransERR is a translation-based knowledge graph embedding model that utilizes efficient relation rotation in the hypercomplex-valued space to enhance translation freedom and improve link prediction performance.
TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
TransERR is a translation-based knowledge graph embedding method that utilizes efficient relation rotation in the hypercomplex-valued space to enhance translation freedom and model various relation patterns effectively.
TransERR: Translation-based Knowledge Graph Embedding via Efficient Relation Rotation
TransERR introduces a translation-based knowledge graph embedding method using efficient relation rotation in the hypercomplex-valued space, enhancing translation freedom for graph embeddings.
Comprehensive Survey on Knowledge Graph Embedding Models and Their Applications
Knowledge graph embedding represents entities and relations in a low-dimensional vector space, capturing the semantic relationships between them, to address the challenges of computational complexity, data sparsity, and manual feature engineering in traditional knowledge graph representations.
Efficient Knowledge Graph Embedding with Conjugate Parameters
Using conjugate parameters for complex numbers employed in knowledge graph embedding models can improve memory efficiency by 2x in relation embedding while achieving comparable performance to state-of-the-art non-conjugate models, with faster or at least comparable training time.
Subgraph2vec: A Flexible Random Walk-Based Algorithm for Embedding Knowledge Graphs
Subgraph2vec is a random walk-based algorithm that embeds knowledge graphs by allowing users to define arbitrary schema subgraphs, providing a more flexible and generic approach compared to previous methods.
Efficient Relation-aware Neighborhood Aggregation in Graph Neural Networks via Tensor Decomposition
A novel graph neural network model that employs tensor decomposition to efficiently integrate relation information with entity representations, improving the expressiveness of the learned embeddings.
A Comprehensive Survey of Recent Random Walk-based Methods for Embedding Knowledge Graphs
Recent random walk-based methods provide a versatile and powerful tool for analyzing and modeling knowledge graphs influenced by randomness.
Flexible and General Knowledge Graph Embedding Model with Block-Diagonal Orthogonal Relation Matrices
The proposed OrthogonalE model employs matrices for entities and block-diagonal orthogonal matrices with Riemannian optimization for relations, enhancing the generality and flexibility of knowledge graph embedding models while capturing diverse relation patterns.
© 2024 by Linnk AI