Search Results for author:
Found 10 papers, 0 papers with code
Knowledge Graph Representation Learning using Ordinary Differential Equations
Many KGEs use the Euclidean geometry which renders them incapable of preserving complex structures and consequently causes wrong inferences by the models.
ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion
Experimental results on benchmark Knowledge Graphs (KGs) such as FB15K and WN18 show that the proposed approach outperforms the state-of-the-art models in entity prediction task using linear and bilinear methods and other recent powerful ones.
LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings
The learning process of such models can be performed by contrasting positive and negative triples.
Trans4E: Link Prediction on Scholarly Knowledge Graphs
This is typical for KGs that categorize a large number of entities (e. g., research articles, patents, persons) according to a relatively small set of categories.
Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings
For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same.
Motif Learning in Knowledge Graphs Using Trajectories Of Differential Equations
To this end, we represent each relation (edge) in a KG as a vector field on a smooth Riemannian manifold.
5* Knowledge Graph Embeddings with Projective Transformations
Most of the embedding models designed in Euclidean geometry usually support a single transformation type - often translation or rotation, which is suitable for learning on graphs with small differences in neighboring subgraphs.
Adaptive Margin Ranking Loss for Knowledge Graph Embeddings via a Correntropy Objective Function
To tackle this problem, several loss functions have been proposed recently by adding upper bounds and lower bounds to the scores of positive and negative samples.
Soft Marginal TransE for Scholarly Knowledge Graph Completion
In this work, the TransE embedding model is reconciled for a specific link prediction task on scholarly metadata.
