Quantum Rationale-Aware Graph Contrastive Learning for Jet Discrimination

2024-11-03

arXiv.org

AI Summary

Quark/gluon jet discrimination in high-energy physics under scarce labeled data remains challenging; existing graph contrastive learning (GCL) methods suffer from insufficient physics-driven augmentation, lack of supervision, and parameter redundancy. Method: We propose Quantum Reasoning-aware Graph Contrastive Learning (QRGCL), a novel framework integrating quantum machine learning, rationale-aware data augmentation, and a lightweight graph neural network. At its core lies a minimal quantum rationale generator (QRG) with only 45 parameters, which produces physically interpretable, quantized rationales to guide both graph-structure augmentation and contrastive learning. Results: On standard jet datasets, QRGCL achieves 77.53% AUC—significantly outperforming classical, quantum, and hybrid GCL and GNN baselines—while using orders-of-magnitude fewer parameters. The framework thus delivers state-of-the-art performance, strong physical interpretability, and computational efficiency simultaneously.

Technology Category

• Machine Learning: Quantum Machine Learning
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In high-energy physics, particle jet tagging plays a pivotal role in distinguishing quark from gluon jets using data from collider experiments. While graph-based deep learning methods have advanced this task beyond traditional feature-engineered approaches, the complex data structure and limited labeled samples present ongoing challenges. However, existing contrastive learning (CL) frameworks struggle to leverage rationale-aware augmentations effectively, often lacking supervision signals that guide the extraction of salient features and facing computational efficiency issues such as high parameter counts. In this study, we demonstrate that integrating a quantum rationale generator (QRG) within our proposed Quantum Rationale-aware Graph Contrastive Learning (QRGCL) framework significantly enhances jet discrimination performance, reducing reliance on labeled data and capturing discriminative features. Evaluated on the quark-gluon jet dataset, QRGCL achieves an AUC score of $77.53%$ while maintaining a compact architecture of only 45 QRG parameters, outperforming classical, quantum, and hybrid GCL and GNN benchmarks. These results highlight QRGCL's potential to advance jet tagging and other complex classification tasks in high-energy physics, where computational efficiency and feature extraction limitations persist.

Problem

• Enhancing quark-gluon jet discrimination using graph contrastive learning
• Overcoming limited labeled data and complex data structure challenges
• Improving computational efficiency and feature extraction in jet tagging

Innovation

• Quantum rationale generator enhances jet discrimination
• Compact architecture with only 45 QRG parameters
• Outperforms classical and quantum GCL benchmarks