# Leveraging universality of jet taggers through transfer learning

arXiv: https://arxiv.org/abs/2203.06210 · HTML: https://mlsanity.com/paper/2203.06210/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 92 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [ParticleNet: Jet Tagging via Particle Clouds](https://mlsanity.com/paper/1902.08570/) (2019)
- [Machine Learning in the Search for New Fundamental Physics](https://mlsanity.com/paper/2112.03769/) (2021)
- [Jet-Images -- Deep Learning Edition](https://mlsanity.com/paper/1511.05190/) (2015)
- [Simulation Assisted Likelihood-free Anomaly Detection](https://mlsanity.com/paper/2001.05001/) (2020)
- [QCD-Aware Recursive Neural Networks for Jet Physics](https://mlsanity.com/paper/1702.00748/) (2017)
- [Jet tagging in the Lund plane with graph networks](https://mlsanity.com/paper/2012.08526/) (2020)
- [Deep learning in color: towards automated quark/gluon jet discrimination](https://mlsanity.com/paper/1612.01551/) (2016)
- [Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets](https://mlsanity.com/paper/1611.04687/) (2016)
- [Recursive Neural Networks in Quark/Gluon Tagging](https://mlsanity.com/paper/1711.02633/) (2017)
- [Interpretable Deep Learning for Two-Prong Jet Classification with Jet Spectra](https://mlsanity.com/paper/1904.02092/) (2019)
- [Spectral Analysis of Jet Substructure with Neural Networks: Boosted Higgs Case](https://mlsanity.com/paper/1807.03312/) (2018)

## Built on by (most cited first, 5 of 5)

- [Finetuning Foundation Models for Joint Analysis Optimization](https://mlsanity.com/paper/2401.13536/) (2024)
- [Fine-tuning machine-learned particle-flow reconstruction for new detector geometries in future colliders](https://mlsanity.com/paper/2503.00131/) (2025)
- [Jet tagging algorithm of graph network with HaarPooling message passing](https://mlsanity.com/paper/2210.13869/) (2022)
- [Vision Transformers for End-to-End Quark-Gluon Jet Classification from Calorimeter Images](https://mlsanity.com/paper/2506.14934/) (2025)
- [A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation](https://mlsanity.com/paper/2607.27501/) (2026)

## Abstract (arXiv)

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.