Particle Transformer for Jet Tagging

Qu, H.; Li, Congqiao; Qian, S. J.

doi:10.48550/arxiv.2202.03772

Cited by 18 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One example of this approach is presented in Ref. [5], where the existing b tagging algorithm used within CMS was enhanced by a Transformer architecture. This increases the selection efficiency of b jets, which is expected to have a direct impact on the reconstruction efficiency of top quarks.…”

Section: Future Applicationsmentioning

confidence: 99%

Machine Learning in Top Physics in the ATLAS and CMS Collaborations

Keicher¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Future Applicationsmentioning

confidence: 99%

Machine Learning in Top Physics in the ATLAS and CMS Collaborations

Keicher¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This poses the question of how to choose a representation of the data for use in density-based anomaly detection tasks. It is also worth noting that despite the great progress that more sophisticated neural network architectures and the implementation of symmetries in networks has brought to supervised classification [48][49][50][51], they have not yet led to the same progress in anomaly detection. In this work we develop a new approach to density-based anomaly detection using self-supervision, which defines the representation of the data in a model-agnostic way using the power of highly expressive networks such as transformers or graph networks to boost anomaly detection performance.…”

Section: Introductionmentioning

confidence: 99%

Anomalies, Representations, and Self-Supervision

Dillon¹,

Favaro²,

Feiden³

et al. 2023

Preprint

View full text Add to dashboard Cite

We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The Anomaly-CLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background representations then computes anomaly scores for a variety of signals in the representation space. With AnomalyCLR we find significant improvements on performance metrics for all signals when compared to the raw data baseline.

show abstract

“…Refs. [1][2][3][4][5][6][7][8]), or to study the properties of Standard Model particles [9], notably to identify boosted electroweak bosons [10][11][12][13], the Higgs boson [14][15][16][17][18][19][20][21], or to assign jet flavour [22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38]. The most challenging scenario is the one in which such heavy objects decay into hadronic jets, in which case the ability to identify them from the decay products is seriously challenged by the overwhelming background arising from QCD jets.…”

Section: Introductionmentioning

confidence: 99%

Leveraging universality of jet taggers through transfer learning

Dreyer,

Grabarczyk,

Monni

2022

Preprint

View full text Add to dashboard Cite

A significant challenge in the tagging of boosted objects via machine-learning technology is the prohibitive computational cost associated with training sophisticated models. Nevertheless, the universality of QCD suggests that a large amount of the information learnt in the training is common to different physical signals and experimental setups. In this article, we explore the use of transfer learning techniques to develop fast and data-efficient jet taggers that leverage such universality. We consider the graph neural networks LundNet and ParticleNet, and introduce two prescriptions to transfer an existing tagger into a new signal based either on fine-tuning all the weights of a model or alternatively on freezing a fraction of them. In the case of W -boson and top-quark tagging, we find that one can obtain reliable taggers using an order of magnitude less data with a corresponding speed-up of the training process. Moreover, while keeping the size of the training data set fixed, we observe a speed-up of the training by up to a factor of three. This offers a promising avenue to facilitate the use of such tools in collider physics experiments.

show abstract

Particle Transformer for Jet Tagging

Cited by 18 publications

References 0 publications

Machine Learning in Top Physics in the ATLAS and CMS Collaborations

Machine Learning in Top Physics in the ATLAS and CMS Collaborations

Anomalies, Representations, and Self-Supervision

Leveraging universality of jet taggers through transfer learning

Contact Info

Product

Resources

About