FMFei Ma
Fei Ma
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Fei Ma has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Feiyi Liu
Chuxiong Normal College
1 shared publication - Wei Li
Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan 430079, China
1 shared publication
Latest Publications
- Open Access
- 9 October 2023
- Published by American Physical Society (APS) in Physical Review D
- Vol. 108 (7) , 072007
Jet tagging algorithm of graph network with Haar pooling message passing
Recently, methods of graph neural networks (GNNs) have been applied to solving the problems in high-energy physics (HEP) and have shown its great potential for quark-gluon tagging with graph representation of jet events. In this paper, we introduce an approach of GNNs combined with a Haar pooling operation to analyze the events, called Haar pooling message passing neural network (HMPNet). In HMPNet, Haar pooling not only extracts the features of graph, but embeds additional information obtained by clustering of means of different particle features. We construct Haar pooling from five different features: absolute energy , transverse momentum , relative coordinates , the mixed ones , and . The results show that an appropriate selection of information for Haar pooling enhances the accuracy of quark-gluon tagging, as adding extra information of to the HMPNet outperforms all the others, whereas adding relative coordinates information is not very effective. This implies that, by adding effective particle features from Haar pooling, one can achieve much better results than that which a solely pure message passing neutral network can do, which demonstrates significant improvement of feature extraction via the pooling process. Finally, we compare the HMPNet study, ordering by , with other studies and prove that the HMPNet is also a good choice of GNN algorithms for jet tagging.- 9 October 2023
- Published by American Physical Society (APS) in Physical Review D
- Vol. 108 (7) , 072007
Open AccessJet tagging algorithm of graph network with Haar pooling message passing
Recently, methods of graph neural networks (GNNs) have been applied to solving the problems in high-energy physics (HEP) and have shown its great potential for quark-gluon tagging with graph representation of jet events. In this paper, we introduce an approach of GNNs combined with a Haar pooling operation to analyze the events, called Haar pooling message passing neural network (HMPNet). In HMPNet, Haar pooling not only extracts the features of graph, but embeds additional information obtained by clustering of means of different particle features. We construct Haar pooling from five different features: absolute energy , transverse momentum , relative coordinates , the mixed ones , and . The results show that an appropriate selection of information for Haar pooling enhances the accuracy of quark-gluon tagging, as adding extra information of to the HMPNet outperforms all the others, whereas adding relative coordinates information is not very effective. This implies that, by adding effective particle features from Haar pooling, one can achieve much better results than that which a solely pure message passing neutral network can do, which demonstrates significant improvement of feature extraction via the pooling process. Finally, we compare the HMPNet study, ordering by , with other studies and prove that the HMPNet is also a good choice of GNN algorithms for jet tagging.