Semi-Equivariant GNN Architectures for Jet Tagging

TL;DR

This paper introduces VecNet, a flexible GNN architecture that combines symmetry-respecting and unconstrained operations, optimizing performance and resource efficiency for jet tagging in high energy physics.

Contribution

The paper proposes VecNet, a novel GNN architecture that allows tuning between symmetry-respecting and unconstrained operations, and introduces the ant factor metric for resource efficiency evaluation.

Findings

VecNet achieves optimal performance with fewer resources.

The ant factor effectively quantifies resource efficiency.

Flexible architecture improves jet tagging performance.

Abstract

Composing Graph Neural Networks (GNNs) of operations that respect physical symmetries has been suggested to give better model performance with a smaller number of learnable parameters. However, real-world applications, such as in high energy physics have not born this out. We present the novel architecture VecNet that combines both symmetry-respecting and unconstrained operations to study and tune the degree of physics-informed GNNs. We introduce a novel metric, the \textit{ant factor}, to quantify the resource-efficiency of each configuration in the search-space. We find that a generalized architecture such as ours can deliver optimal performance in resource-constrained applications.