PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction
arXiv:2402.11538 · doi:10.1088/2632-2153/ad8060
Abstract
In high-energy physics, particles produced in collision events decay in a format of a hierarchical tree structure, where only the final decay products can be observed using detectors. However, the large combinatorial space of possible tree structures makes it challenging to recover the actual decay process given a set of final particles. To better analyse the hierarchical tree structure, we propose a graph-based deep learning model to infer the tree structure to reconstruct collision events. In particular, we use a compact matrix representation termed as lowest common ancestor generations (LCAG) matrix, to encode the particle decay tree structure. Then, we introduce a perturbative augmentation technique applied to node features, aiming to mimic experimental uncertainties and increase data diversity. We further propose a supervised graph contrastive learning algorithm to utilize the information of inter-particle relations from multiple decay processes. Extensive experiments show that our proposed supervised graph contrastive learning with perturbative augmentation (PASCL) method outperforms state-of-the-art baseline models on an existing physics-based dataset, significantly improving the reconstruction accuracy. This method provides a more effective training strategy for models with the same parameters and makes way for more accurate and efficient high-energy particle physics data analysis.
References in corpus (13)
- Molecular Contrastive Learning of Representations via Graph Neural Networks
- Deep Learning and its Application to LHC Physics
- Graph Neural Networks in Particle Physics
- The Full Event Interpretation -- An exclusive tagging algorithm for the Belle II experiment
- A Living Review of Machine Learning for Particle Physics
- Supervised Jet Clustering with Graph Neural Networks for Lorentz Boosted Bosons
- Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
- The Boosted Higgs Jet Reconstruction via Graph Neural Network
- Reconstructing particles in jets using set transformer and hypergraph prediction networks
- Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
- Secondary Vertex Finding in Jets with Neural Networks
- Learning Tree Structures from Leaves For Particle Decay Reconstruction
- Parton Labeling without Matching: Unveiling Emergent Labelling Capabilities in Regression Models