most citedInterpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs

33 citations · 33 across the 1 of their papers we have counts for

collaborators

1 paper

cs.LG2018★ 33 cited

Interpretable Graph Convolutional Neural Networks for Inference on Noisy Knowledge Graphs

Daniel Neil, Joss Briody, Alix Lacoste +3

In this work, we provide a new formulation for Graph Convolutional Neural Networks (GCNNs) for link prediction on graph data that addresses common challenges for biomedical knowled…