E-PCN: Jet Tagging with Explainable Particle Chebyshev Networks Using Kinematic Features

TL;DR

E-PCN is an explainable graph neural network for jet classification that leverages kinematic features and Grad-CAM to interpret decision-making, achieving high accuracy and interpretability.

Contribution

The paper introduces E-PCN, an extension of PCN that incorporates multiple kinematic features and uses Grad-CAM for interpretability in jet classification.

Findings

E-PCN achieves 94.67% macro-accuracy on JetClass dataset.

Angular separation and transverse momentum dominate classification decisions.

E-PCN outperforms baseline PCN by over 2% in accuracy and 4% in AUC.

Abstract

The identification and classification of collimated particle sprays, or jets, are essential for interpreting data from high-energy collider experiments. While deep learning has improved jet classification, it often lacks interpretability. We introduce the Explainable Particle Chebyshev Network (E-PCN), a graph neural network extending the Particle Chebyshev Network (PCN). E-PCN integrates kinematic variables into jet classification by constructing four graph representations per jet, each weighted by a distinct variable: angular separation ($\Delta$), transverse momentum ($k_T$), momentum fraction ($z$), and invariant mass squared ($m^2$). We use the concept of Gradient-weighted Class Activation Mapping (Grad-CAM) to determine which kinematic variables dominate classification outcomes. Analysis reveals that angular separation and transverse momentum collectively account for approximately 76% of classification decisions (40.72% and 35.67%, respectively), with momentum fraction and invariant mass contributing the remaining 24%. Evaluated on the JetClass dataset with 10 signal classes, E-PCN achieves a macro-accuracy of 94.67%, macro-AUC of 96.78%, and macro-AUPR of 86.79%, representing improvements of 2.36%, 4.13%, and 24.88% respectively over the baseline PCN implementation, while demonstrating physically interpretable feature learning.