Integrating Physics Inspired Features with Graph Convolution

2024-03-18

AI Summary

To address insufficient classification accuracy in quark–gluon jet discrimination within high-energy physics, this work proposes CapsLorentzNet: the first integration of capsule networks into the decoder of a Lorentz-invariant graph neural network (LorentzNet). By employing vector neurons, CapsLorentzNet explicitly models particle directionality and existence, while reconstruction-based regularization incorporates expert-designed physical features. This design enables synergistic modeling of physical priors—including Lorentz covariance and particle geometric structure—with deep learning, achieving architecture-agnostic compatibility and seamless integration with arbitrary GNN backbones. On the standard quark–gluon tagging benchmark, CapsLorentzNet improves classification performance by 20% over the original LorentzNet, while substantially enhancing both physical interpretability and generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Learning & Optimization for CV
• Natural Language Processing: Learning & Optimization for NLP

Application Category

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

Abstract

With the advent of advanced machine learning techniques, boosted object tagging has witnessed significant progress. In this article, we take this field further by introducing novel architectural modifications compatible with a wide array of Graph Neural Network (GNN) architectures. Our approach advocates for integrating capsule layers, replacing the conventional decoding blocks in standard GNNs. These capsules are a group of neurons with vector activations. The orientation of these vectors represents important properties of the objects under study, with their magnitude characterizing whether the object under study belongs to the class represented by the capsule. Moreover, capsule networks incorporate a regularization by reconstruction mechanism, facilitating the seamless integration of expert-designed high-level features into the analysis. We have studied the usefulness of our architecture with the LorentzNet architecture for quark-gluon tagging. Here, we have replaced the decoding block of LorentzNet with a capsulated decoding block and have called the resulting architecture CapsLorentzNet. Our new architecture can enhance the performance of LorentzNet by 20 % for the quark-gluon tagging task.

Problem

• Object Recognition
• Quark-Gluon Discrimination
• Graph Neural Networks

Innovation

• Capsule Layers
• Graph Neural Networks
• Quark-Gluon Discrimination