Publications
Publication Information
| Title | Domain-Adversarial Graph Neural Networks for Lambda Hyperon Identification with CLAS12 |
| Authors | Matthew McEneaney, Anselm Vossen |
| JLAB number | JLAB-PHY-23-3755 |
| LANL number | arXiv:2302.05481 |
| Other number | DOE/OR/23177-5712 |
| Document Type(s) | (Journal Article) |
| Associated with EIC: | No |
| Supported by Jefferson Lab LDRD Funding: | No |
| Funding Source: | Nuclear Physics (NP) |
|
Journal Compiled for Journal of Instrumentation Volume 18 Page(s) P06002 Refereed | |
| Publication Abstract: | Machine learning methods and in particular Graph Neural Networks (GNNs) have revolutionized many tasks within the high energy physics community. We report on the novel use of GNNs and a domain-adversarial training method to identify ? hyperon events with the CLAS12 experiment at Jefferson Lab. The GNN method we have developed increases the purity of the ? yield by a factor of 1.95 and by 1.82 using the domain-adversarial training. This work also provides a good benchmark for developing event tagging machine learning methods for the ? and other channels at CLAS12 and other experiments, such as the planned Electron Ion Collider. |
| Experiment Numbers: | |
| Group: | Hall B |
| Document: | |
| DOI: | http://dx.doi.org/10.1088/1748-0221/18/06/P06002 |
| Accepted Manuscript: | |
| Supporting Documents: | |
| Supporting Datasets: | |