Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
This work addresses anomaly detection for particle physics researchers, but it is incremental as it builds on existing autoencoder and graph neural network methods.
The authors tackled the problem of anomaly detection in high-energy physics jets by developing graph-based autoencoders that leverage particle interdependencies, and they introduced a differentiable approximation to the energy mover's distance using a graph neural network for use as a reconstruction loss.
Autoencoders have useful applications in high energy physics in anomaly detection, particularly for jets - collimated showers of particles produced in collisions such as those at the CERN Large Hadron Collider. We explore the use of graph-based autoencoders, which operate on jets in their "particle cloud" representations and can leverage the interdependencies among the particles within a jet, for such tasks. Additionally, we develop a differentiable approximation to the energy mover's distance via a graph neural network, which may subsequently be used as a reconstruction loss function for autoencoders.