ABCNet: An attention-based method for particle tagging

In high energy physics, graph-based implementations have the advantage of treating the input data sets in a similar way as they are collected by collider experiments. To expand on this concept, we propose a graph neural network enhanced by attention mechanisms called ABCNet. To exemplify the advantages and flexibility of treating collider data as a point cloud, two physically motivated problems are investigated: quark–gluon discrimination and pileup reduction. The former is an event-by-event classification, while the latter requires each reconstructed particle to receive a classification score. For both tasks, ABCNet shows an improved performance compared to other algorithms available.

Download paper here

Algorithm implementation

Recommended citation:

@article{Mikuni:2020wpr,
    author = "Mikuni, Vinicius and Canelli, Florencia",
    title = "{ABCNet: An attention-based method for particle tagging}",
    eprint = "2001.05311",
    archivePrefix = "arXiv",
    primaryClass = "physics.data-an",
    reportNumber = "135",
    doi = "10.1140/epjp/s13360-020-00497-3",
    journal = "Eur. Phys. J. Plus",
    volume = "135",
    number = "6",
    pages = "463",
    year = "2020"
}