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.
| Comments: | 25 pages, 3 figures |
| Subjects: | High Energy Physics - Phenomenology (hep-ph); Machine Learning (cs.LG); High Energy Physics - Experiment (hep-ex) |
| Cite as: | arXiv:2512.07420 [hep-ph] |
| (or arXiv:2512.07420v2 [hep-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2512.07420 arXiv-issued DOI via DataCite |
From: Mir Sazzat Hossain [view email]
[v1]
Mon, 8 Dec 2025 10:53:05 UTC (378 KB)
[v2]
Sun, 3 May 2026 16:42:22 UTC (1,079 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。