Search Results for author:
Found 3 papers, 2 papers with code
TripleRE: Knowledge Graph Embeddings via Tripled Relation Vectors
Translation-based knowledge graph embedding has been one of the most important branches for knowledge representation learning since TransE came out.
StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph
Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector, ignoring the rich information contained in the neighborhood.
Ranked #6 on
Link Property Prediction
on ogbl-wikikg2
Reinterpreting CTC training as iterative fitting
The outputs of a CTC-trained model tend to form a series of spikes separated by strongly predicted blanks, know as the spiky problem.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
