{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T15:48:38Z","timestamp":1753890518841,"version":"3.41.2"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T00:00:00Z","timestamp":1712793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>Particle accelerators play a crucial role in scientific research, enabling the study of fundamental physics and materials science, as well as having important medical applications. This study proposes a novel graph learning approach to classify operational beamline configurations as good or bad. By considering the relationships among beamline elements, we transform data from components into a heterogeneous graph. We propose to learn from historical, unlabeled data via our self-supervised training strategy along with fine-tuning on a smaller, labeled dataset. Additionally, we extract a low-dimensional representation from each configuration that can be visualized in two dimensions. Leveraging our ability for classification, we map out regions of the low-dimensional latent space characterized by good and bad configurations, which in turn can provide valuable feedback to operators. This research demonstrates a paradigm shift in how complex, many-dimensional data from beamlines can be analyzed and leveraged for accelerator operations.<\/jats:p>","DOI":"10.3389\/fdata.2024.1366469","type":"journal-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T04:59:12Z","timestamp":1712811552000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph learning for particle accelerator operations"],"prefix":"10.3389","volume":"7","author":[{"given":"Song","family":"Wang","sequence":"first","affiliation":[]},{"given":"Chris","family":"Tennant","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Moser","sequence":"additional","affiliation":[]},{"given":"Theo","family":"Larrieu","sequence":"additional","affiliation":[]},{"given":"Jundong","family":"Li","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2024,4,11]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","DOI":"10.1145\/3487553.3524722","article-title":"\u201cJgcl: joint self-supervised and supervised graph contrastive learning,\u201d","author":"Akkas","year":"2022","journal-title":"WWW '22: Companion Proceedings of the Web Conference 2022"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1016\/j.patcog.2010.12.015","article-title":"Supervised principal component analysis: visualization, classification and regression on subspaces and submanifolds","volume":"44","author":"Barshan","year":"2011","journal-title":"Patt. Recognit"},{"key":"B3","doi-asserted-by":"crossref","DOI":"10.1142\/8635","author":"Br\u00fcning","year":"2016","journal-title":"Challenges and Goals for Accelerators in the XXI Century"},{"key":"B4","article-title":"\u201cHeterogeneous network embedding via deep architectures,\u201d","author":"Chang","year":"2015","journal-title":"SIGKDD"},{"key":"B5","article-title":"\u201cFast graph representation learning with PyTorch Geometric,\u201d","author":"Fey","year":"2019","journal-title":"ICLR Workshop on Representation Learning on Graphs and Manifolds"},{"key":"B6","article-title":"\u201cContrastive prototype learning with augmented embeddings for few-shot learning,\u201d","author":"Gao","year":"2021","journal-title":"UAI"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2202.07179","article-title":"G-mixup: graph data augmentation for graph classification","author":"Han","year":"2022","journal-title":"arXiv"},{"key":"B8","article-title":"\u201cContrastive multi-view representation learning on graphs,\u201d","author":"Hassani","year":"2020","journal-title":"ICML"},{"key":"B9","article-title":"\u201cHeterogeneous graph attention networks for semi-supervised short text classification,\u201d","author":"Hu","year":"2019","journal-title":"EMNLP-IJCNLP"},{"key":"B10","article-title":"\u201cHeterogeneous graph transformer,\u201d","author":"Hu","year":"2020","journal-title":"TheWebConf"},{"key":"B11","article-title":"\u201cMulti-scale contrastive siamese networks for self-supervised graph representation learning,\u201d","author":"Jin","year":"2021","journal-title":"IJCAI"},{"key":"B12","article-title":"\u201cSupervised contrastive learning,\u201d","author":"Khosla","year":"2020","journal-title":"NeurIPS"},{"key":"B13","article-title":"\u201cAdam: A method for stochastic optimization,\u201d","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"B14","article-title":"\u201cSemi-supervised classification with graph convolutional networks,\u201d","author":"Kipf","year":"2017","journal-title":"ICLR"},{"key":"B15","doi-asserted-by":"publisher","first-page":"107398","DOI":"10.1016\/j.ymssp.2020.107398","article-title":"1D convolutional neural networks and applications: a survey","volume":"151","author":"Kiranyaz","year":"2021","journal-title":"Mech. Syst. Signal Process"},{"key":"B16","article-title":"\u201cDeeper insights into graph convolutional networks for semi-supervised learning,\u201d","author":"Li","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32"},{"key":"B17","article-title":"\u201cHeterogeneous similarity graph neural network on electronic health records,\u201d","author":"Liu","year":"2020","journal-title":"IEEE Big Data"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.03748","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018","journal-title":"arXiv"},{"key":"B20","article-title":"\u201cAutomatic differentiation in pytorch,\u201d","author":"Paszke","year":"2017","journal-title":"NeurIPS"},{"key":"B21","article-title":"\u201cScikit-learn: machine learning in python,\u201d","author":"Pedregosa","year":"2011","journal-title":"JMLR"},{"key":"B22","article-title":"\u201cGcc: Graph contrastive coding for graph neural network pre-training,\u201d","author":"Qiu","year":"2020","journal-title":"SIGKDD"},{"key":"B23","doi-asserted-by":"publisher","first-page":"124801","DOI":"10.1103\/PhysRevAccelBeams.19.124801","article-title":"Continuous wave superconducting radio frequency electron linac for nuclear physics research","volume":"19","author":"Reece","year":"2016","journal-title":"Phys. Rev. Accel. Beams"},{"key":"B24","doi-asserted-by":"publisher","first-page":"15920","DOI":"10.48550\/arXiv.2106.05819","article-title":"Adversarial graph augmentation to improve graph contrastive learning","volume":"34","author":"Suresh","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B25","first-page":"225","article-title":"\u201cMaps for the visualization of high-dimensional data spaces,\u201d","author":"Ultsch","year":"2003","journal-title":"Proc. Workshop on Self Organizing Maps"},{"key":"B26","article-title":"\u201cVisualizing data using t-sne,\u201d","author":"Van der Maaten","year":"2008","journal-title":"JMLR"},{"journal-title":"Graph Attention Networks","year":"2018","author":"Veli\u010dkovi\u0107","key":"B27"},{"key":"B28","article-title":"\u201cDeep graph infomax,\u201d","author":"Velickovic","year":"2019","journal-title":"ICLR"},{"key":"B29","article-title":"\u201cContrastive graph poisson networks: semi-supervised learning with extremely limited labels,\u201d","author":"Wan","year":"2021","journal-title":"NeurIPS"},{"key":"B30","article-title":"\u201cSimplifying graph convolutional networks,\u201d","author":"Wu","year":"2019","journal-title":"ICML"},{"key":"B31","article-title":"\u201cHow powerful are graph neural networks?,\u201d","author":"Xu","year":"2019","journal-title":"ICLR"},{"key":"B32","article-title":"\u201cHierarchical graph representation learning with differentiable pooling,\u201d","author":"Ying","year":"2018","journal-title":"NeurIPS"},{"key":"B33","article-title":"\u201cGraph contrastive learning with augmentations,\u201d","author":"You","year":"2020","journal-title":"NeurIPS"},{"key":"B34","article-title":"\u201cGraph contrastive learning with adaptive augmentation,\u201d","author":"Zhu","year":"2021","journal-title":"TheWebConf"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1366469\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T04:59:27Z","timestamp":1712811567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1366469\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,11]]},"references-count":34,"alternative-id":["10.3389\/fdata.2024.1366469"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2024.1366469","relation":{},"ISSN":["2624-909X"],"issn-type":[{"type":"electronic","value":"2624-909X"}],"subject":[],"published":{"date-parts":[[2024,4,11]]},"article-number":"1366469"}}