Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks

no code implementations • 30 Sep 2020 • Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias

In this work, we propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models, particularly against poisoning attacks to the graph structure, by leveraging epistemic uncertainties from the message passing framework.

Graph Classification Link Prediction +1

A Regularized Attention Mechanism for Graph Attention Networks

no code implementations • 1 Nov 2018 • Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias

Machine learning models that can exploit the inherent structure in data have gained prominence.

Graph Attention

Attention Models with Random Features for Multi-layered Graph Embeddings

no code implementations • 2 Oct 2018 • Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Huan Song, Andreas Spanias

Though deep network embeddings, e. g. DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective.

Network Embedding Node Classification