Abstract: Negative sampling is an essential part in knowledge graph embedding, which offers significant advantages to numerous downstream related tasks. There are two kinds of important negatives: ...
Abstract: Graph Contrastive Learning (GCL), a Self-Supervised Learning (SSL) architecture tailored for graphs, has shown notable potential for mitigating label scarcity. Its core idea is to amplify ...
Center for Cooperative Research on Alternative Energies (CIC energiGUNE), Basque Research and Technology Alliance (BRTA), Parque Tecnológico de Álava, Albert Einstein, 48, 01510 Vitoria-Gasteiz, Spain ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results