Two papers about GNNs accepted at KDD 2020


We have two papers at this year’s KDD:

  • "Scaling Graph Neural Networks with Approximate PageRank": In collaboration with colleagues from Google Research we have developed a highly scalable GNN able to handle massive graphs in single-machine and distributed environments. The paper got accepted as on oral.
  • “Certifiable Robustness of Graph Convolutional Networks under Structure Perturbations”: In this work we studied robustness certification of GNNs under potential changes to the network structure, i.e. giving guarantees about the predictions even under adversarial changes to the graph.

Congratulations to all co-authors!