Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction (2402.11538v1)

Published 18 Feb 2024 in hep-ph and cs.LG

Abstract: In high-energy physics, particles produced in collision events decay in a format of a hierarchical tree structure, where only the final decay products can be observed using detectors. However, the large combinatorial space of possible tree structures makes it challenging to recover the actual decay process given a set of final particles. To better analyse the hierarchical tree structure, we propose a graph-based deep learning model to infer the tree structure to reconstruct collision events. In particular, we use a compact matrix representation termed as lowest common ancestor generations (LCAG) matrix, to encode the particle decay tree structure. Then, we introduce a perturbative augmentation technique applied to node features, aiming to mimic experimental uncertainties and increase data diversity. We further propose a supervised graph contrastive learning algorithm to utilize the information of inter-particle relations from multiple decay processes. Extensive experiments show that our proposed supervised graph contrastive learning with perturbative augmentation (PASCL) method outperforms state-of-the-art baseline models on an existing physics-based dataset, significantly improving the reconstruction accuracy. This method provides a more effective training strategy for models with the same parameters and makes way for more accurate and efficient high-energy particle physics data analysis.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. LHC Machine. JINST, 3:S08001, 2008.
  2. T. Abe et al. Belle II Technical Design Report. 11 2010.
  3. Topological reconstruction of particle physics processes using graph neural networks. Phys. Rev. D, 107(11):116019, 2023.
  4. T. Keck et al. The Full Event Interpretation: An Exclusive Tagging Algorithm for the Belle II Experiment. Comput. Softw. Big Sci., 3(1):6, 2019.
  5. Deep learning and its application to lhc physics. Annual Review of Nuclear and Particle Science, 68:161–181, 2018.
  6. Machine learning in high energy physics community white paper. In Journal of Physics: Conference Series, volume 1085, page 022008. IOP Publishing, 2018.
  7. HEP ML Community. A Living Review of Machine Learning for Particle Physics.
  8. Graph neural networks in particle physics. Machine Learning: Science and Technology, 2(2):021001, 2020.
  9. Graph neural networks at the Large Hadron Collider. Nature Rev. Phys., 5(5):281–303, 2023.
  10. The hep. trkx project: deep neural networks for hl-lhc online and offline tracking. In EPJ Web of Conferences, volume 150, page 00003. EDP Sciences, 2017.
  11. Performance of a geometric deep learning pipeline for hl-lhc particle tracking. The European Physical Journal C, 81:1–14, 2021.
  12. Multi-particle reconstruction in the High Granularity Calorimeter using object condensation and graph neural networks. EPJ Web Conf., 251:03072, 2021.
  13. Progress towards an improved particle flow algorithm at CMS with machine learning. In 21th International Workshop on Advanced Computing and Analysis Techniques in Physics Research: AI meets Reality, 3 2023.
  14. Reconstructing particles in jets using set transformer and hypergraph prediction networks. The European Physical Journal C, 83(7), July 2023.
  15. Secondary vertex finding in jets with neural networks. The European Physical Journal C, 81(6):540, 2021.
  16. Neural message passing for jet physics. 2017.
  17. Learning tree structures from leaves for particle decay reconstruction. Machine Learning: Science and Technology, 3(3):035012, 2022.
  18. GNN for Deep Full Event Interpretation and Hierarchical Reconstruction of Heavy-Hadron Decays in Proton–Proton Collisions. Comput. Softw. Big Sci., 7(1):12, 2023.
  19. Contrastive multiview coding. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XI 16, pages 776–794. Springer, 2020.
  20. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  21. Eda: Easy data augmentation techniques for boosting performance on text classification tasks. arXiv preprint arXiv:1901.11196, 2019.
  22. Videomix: Rethinking data augmentation for video classification. arXiv preprint arXiv:2012.03457, 2020.
  23. Survey on videos data augmentation for deep learning models. Future Internet, 14(3):93, 2022.
  24. Graph contrastive learning with adaptive augmentation. In Proceedings of the Web Conference 2021, pages 2069–2080, 2021.
  25. Simple gnn regularisation for 3d molecular property prediction & beyond. arXiv preprint arXiv:2106.07971, 2021.
  26. Nodeaug: Semi-supervised node classification with data augmentation. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 207–217, 2020.
  27. Dropedge: Towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903, 2019.
  28. Deep graph contrastive representation learning. arXiv preprint arXiv:2006.04131, 2020.
  29. Graph contrastive learning with augmentations. Advances in neural information processing systems, 33:5812–5823, 2020.
  30. Deep graph infomax. arXiv preprint arXiv:1809.10341, 2018.
  31. Local augmentation for graph neural networks. In International Conference on Machine Learning, pages 14054–14072. PMLR, 2022.
  32. Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9729–9738, 2020.
  33. Molecular contrastive learning of representations via graph neural networks. Nature Machine Intelligence, 4(3):279–287, 2022.
  34. Cloome: contrastive learning unlocks bioimaging databases for queries with chemical structures. Nature Communications, 14(1):7339, 2023.
  35. Knowledge graph-enhanced molecular contrastive learning with functional prompt. Nature Machine Intelligence, pages 1–12, 2023.
  36. Robust optimization as data augmentation for large-scale graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 60–69, 2022.
  37. Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083, 2017.
  38. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009, 2022.
  39. Supervised contrastive learning. Advances in neural information processing systems, 33:18661–18673, 2020.
  40. Clusterscl: cluster-aware supervised contrastive learning on graphs. In Proceedings of the ACM Web Conference 2022, pages 1611–1621, 2022.
  41. Neural relational inference for interacting systems. In International conference on machine learning, pages 2688–2697. PMLR, 2018.
  42. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.
  43. Supervised contrastive learning for pre-trained language model fine-tuning. arXiv preprint arXiv:2011.01403, 2020.
  44. Lowest common ancestor generations (lcag) phasespace particle decay reconstruction dataset. 2022.
  45. phasespace: n-body phase space generation in python. Journal of Open Source Software, 4(42):1570, 2019.
  46. Factorised neural relational inference for multi-interaction systems. arXiv preprint arXiv:1905.08721, 2019.
  47. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  48. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  49. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), 38(5):1–12, 2019.
  50. Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
  51. A cluster separation measure. IEEE transactions on pattern analysis and machine intelligence, (2):224–227, 1979.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets