Recursive Neural Networks in Quark/Gluon Tagging

TL;DR

This paper investigates the use of recursive neural networks, leveraging jet clustering history, for improved quark/gluon jet discrimination, showing modest performance gains over traditional methods and insights into feature importance.

Contribution

It demonstrates that RecNNs, utilizing jet tree structures, outperform baseline classifiers in quark/gluon tagging and reveals that particle flow features alone contain significant discriminative information.

Findings

RecNNs outperform BDT by a few percent in gluon rejection.

Particle flow identification alone provides strong discrimination.

Tree-structure features capture most information needed for quark/gluon separation.

Abstract

Since the machine learning techniques are improving rapidly, it has been shown that the image recognition techniques in deep neural networks can be used to detect jet substructure. And it turns out that deep neural networks can match or outperform traditional approach of expert features. However, there are disadvantages such as sparseness of jet images. Based on the natural tree-like structure of jet sequential clustering, the recursive neural networks (RecNNs), which embed jet clustering history recursively as in natural language processing, have a better behavior when confronted with these problems. We thus try to explore the performance of RecNNs in quark/gluon discrimination. The results show that RecNNs work better than the baseline boosted decision tree (BDT) by a few percent in gluon rejection rate. However, extra implementation of particle flow identification only increases the performance slightly. We also experimented on some relevant aspects which might influence the performance of the networks. It shows that even taking only particle flow identification as input feature without any extra information on momentum or angular position is already giving a fairly good result, which indicates that the most of the information for quark/gluon discrimination is already included in the tree-structure itself. As a bonus, a rough up/down quark jets discrimination is also explored.