# Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks

arXiv: https://arxiv.org/abs/2010.09206 · HTML: https://mlsanity.com/paper/2010.09206/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 22 of 22)

- [Scalars are universal: Equivariant machine learning, structured like classical physics](https://mlsanity.com/paper/2106.06610/) (2021)
- [Masked Particle Modeling on Sets: Towards Self-Supervised High Energy Physics Foundation Models](https://mlsanity.com/paper/2401.13537/) (2024)
- [The Exact Sample Complexity Gain from Invariances for Kernel Regression](https://mlsanity.com/paper/2303.14269/) (2023)
- [Point Cloud Transformers applied to Collider Physics](https://mlsanity.com/paper/2102.05073/) (2021)
- [Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principles](https://mlsanity.com/paper/2301.05638/) (2023)
- [End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics](https://mlsanity.com/paper/2305.10399/) (2023)
- [SPANet: Generalized Permutationless Set Assignment for Particle Physics using Symmetry Preserving Attention](https://mlsanity.com/paper/2106.03898/) (2021)
- [Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges](https://mlsanity.com/paper/2203.12852/) (2022)
- [nu-Flows: Conditional Neutrino Regression](https://mlsanity.com/paper/2207.00664/) (2022)
- [Snowmass 2021 Computational Frontier CompF03 Topical Group Report: Machine Learning](https://mlsanity.com/paper/2209.07559/) (2022)
- [nu2-Flows: Fast and improved neutrino reconstruction in multi-neutrino final states with conditional normalizing flows](https://mlsanity.com/paper/2307.02405/) (2023)
- [Topological Reconstruction of Particle Physics Processes using Graph Neural Networks](https://mlsanity.com/paper/2303.13937/) (2023)
- [The Quarks of Attention](https://mlsanity.com/paper/2202.08371/) (2022)
- [Reconstruction of Unstable Heavy Particles Using Deep Symmetry-Preserving Attention Networks](https://mlsanity.com/paper/2309.01886/) (2023)
- [Oracle-Preserving Latent Flows](https://mlsanity.com/paper/2302.00806/) (2023)
- [Optimal Equivariant Architectures from the Symmetries of Matrix-Element Likelihoods](https://mlsanity.com/paper/2410.18553/) (2024)
- [Reconstructing short-lived particles using hypergraph representation learning](https://mlsanity.com/paper/2402.10149/) (2024)
- [PASCL: Supervised Contrastive Learning with Perturbative Augmentation for Particle Decay Reconstruction](https://mlsanity.com/paper/2402.11538/) (2024)
- [Reconstruction of boosted and resolved multi-Higgs-boson events with symmetry-preserving attention networks](https://mlsanity.com/paper/2412.03819/) (2024)
- [Unknown Unknowns: Model Misspecification in Machine Learning for Physics](https://mlsanity.com/paper/2608.13633/) (2026)
- [Pairton: Iterative Reconstruction of Short-Lived Particles](https://mlsanity.com/paper/2608.14278/) (2026)
- [Comprehensive reconstruction of collider events with hypergraph representation learning and graph-conditioned diffusion](https://mlsanity.com/paper/2609.18928/) (2026)

## Abstract (arXiv)

Top quarks, produced in large numbers at the Large Hadron Collider, have a complex detector signature and require special reconstruction techniques. The most common decay mode, the "all-jet" channel, results in a 6-jet final state which is particularly difficult to reconstruct in pp collisions due to the large number of permutations possible. We present a novel approach to this class of problem, based on neural networks using a generalized attention mechanism, that we call Symmetry Preserving Attention Networks (SPA-Net). We train one such network to identify the decay products of each top quark unambiguously and without combinatorial explosion as an example of the power of this technique.This approach significantly outperforms existing state-of-the-art methods, correctly assigning all jets in 93.0% of 6-jet, 87.8% of 7-jet, and 82.6% of ≥ 8-jet events respectively.