# KIGNet: Physics-Motivated Multi-Graph Representation Learning for Explainable Jet Tagging

arXiv: https://arxiv.org/abs/2512.07420 · HTML: https://mlsanity.com/paper/2512.07420/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 54 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Lorentz Group Equivariant Neural Network for Particle Physics](https://mlsanity.com/paper/2006.04780/) (2020)
- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [Energy Flow Networks: Deep Sets for Particle Jets](https://mlsanity.com/paper/1810.05165/) (2018)
- [ParticleNet: Jet Tagging via Particle Clouds](https://mlsanity.com/paper/1902.08570/) (2019)
- [Machine Learning in High Energy Physics Community White Paper](https://mlsanity.com/paper/1807.02876/) (2018)
- [Jet-Images -- Deep Learning Edition](https://mlsanity.com/paper/1511.05190/) (2015)
- [PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics](https://mlsanity.com/paper/2211.00454/) (2022)
- [Point Cloud Transformers applied to Collider Physics](https://mlsanity.com/paper/2102.05073/) (2021)
- [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)
- [Aspen Open Jets: Unlocking LHC Data for Foundation Models in Particle Physics](https://mlsanity.com/paper/2412.10504/) (2024)
- [Particle Convolution for High Energy Physics](https://mlsanity.com/paper/2107.02908/) (2021)
- [Jet tagging algorithm of graph network with HaarPooling message passing](https://mlsanity.com/paper/2210.13869/) (2022)
- [PCN: A Deep Learning Approach to Jet Tagging Utilizing Novel Graph Construction Methods and Chebyshev Graph Convolutions](https://mlsanity.com/paper/2309.08630/) (2023)
- [Spatially Aware Linear Transformer (SAL-T) for Particle Jet Tagging](https://mlsanity.com/paper/2510.23641/) (2025)

## Built on by (most cited first, 1 of 1)

- [Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane](https://mlsanity.com/paper/2604.25885/) (2026)

## Abstract (arXiv)

Jet identification plays a central role in analyzing data from high-energy collider experiments. While deep learning has improved jet classification, it often lacks interpretability. We introduce the Kinematic Interaction Graph Network (KIGNet), a graph neural network that integrates kinematic variables into jet classification by constructing four graph representations per jet, each weighted by a distinct variable: angular separation (Delta), relative transverse momentum (kT), momentum fraction (z), and invariant mass squared (m2). Three of these (Delta, kT, z) are motivated by the Lund jet plane, grounded in perturbative QCD factorization; the fourth (m2) adds complementary mass-scale sensitivity for heavy-flavor identification. Using Gradient-weighted Class Activation Mapping (Grad-CAM), we determine which variables dominate classification. Angular separation and relative transverse momentum account for about 76% of the total Grad-CAM attribution (40.72% and 35.67%), with momentum fraction and invariant mass contributing the remaining 24%. This hierarchy is consistent with the soft-collinear structure of QCD radiation in the training data, showing that the network learns physically interpretable representations rather than spurious correlations. On the JetClass dataset, KIGNet achieves a macro-accuracy of 95.07%, macro-AUC of 96.61%, and macro-AUPR of 81.52%, relative improvements of 2.45%, 3.40%, and 19.11% over the state-of-the-art baseline. On the Aspen Open Jets dataset of real CMS collision data, KIGNet produces substantially more structured latent representations than the baseline, reducing the Davies-Bouldin Index by 52.15% (0.8395 rightarrow 0.4017) and increasing the Dunn Index by 42.33% (0.0189 rightarrow 0.0269), confirming that physics-informed kinematic encoding generalizes beyond idealized simulation to experimental detector conditions.