Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
This addresses the challenge of efficiently reconstructing particle physics processes for researchers, though it is incremental as it matches rather than surpasses existing state-of-the-art methods.
The paper tackles the problem of reconstructing particle physics processes by introducing Topograph, a method that uses graph neural networks to assign final state objects to mother particles and predict intermediate particle properties, achieving performance matching state-of-the-art machine learning techniques in top quark pair production.
We present a new approach, the Topograph, which reconstructs underlying physics processes, including the intermediary particles, by leveraging underlying priors from the nature of particle physics decays and the flexibility of message passing graph neural networks. The Topograph not only solves the combinatoric assignment of observed final state objects, associating them to their original mother particles, but directly predicts the properties of intermediate particles in hard scatter processes and their subsequent decays. In comparison to standard combinatoric approaches or modern approaches using graph neural networks, which scale exponentially or quadratically, the complexity of Topographs scales linearly with the number of reconstructed objects. We apply Topographs to top quark pair production in the all hadronic decay channel, where we outperform the standard approach and match the performance of the state-of-the-art machine learning technique.