Machine Learning on Networks

We detail the challanges to performing coordination detecition on social media in a responsible way, and propose a framework to meet these challanges. The framework is then used to form a specific detector, which detects a number of coordinated campaigns in a real Twitter dataset.

The deep learning approach to graph classification is to embed nodes in a latent space, typically graph convolutions, and then to use these embeddings to make a single classification. The number of nodes may differ from one training example to the next, which poses a problem. We demonstrate that the node embedding distribution can be approximated using differentiable histograms. After the histograms are created, traditional convolutional layers can be used to classify the graph. This procedure leverages all available information, regardless of how the size of graphs vary. We demonstrate that this architecture gives incremental improvement for various benchmark datasets. We use this approach to classify bots on Twitter based on their communication graph. We find this classification technique generalizes better than previous methods, however sacrifices some precision.