EggNet: An Evolving Graph-based Graph Attention Network for Particle Track Reconstruction

TL;DR

EggNet introduces an evolving graph attention network that reconstructs particle tracks directly from hit data, improving scalability and performance over fixed-graph methods in particle physics experiments.

Contribution

It proposes a novel one-shot object condensation approach with recursive graph attention and evolving graph structures for particle track reconstruction.

Findings

Outperforms fixed-graph methods on TrackML dataset

Demonstrates improved scalability and accuracy

Uses recursive graph updates for better message passing

Abstract

Track reconstruction is a crucial task in particle experiments and is traditionally very computationally expensive due to its combinatorial nature. Recently, graph neural networks (GNNs) have emerged as a promising approach that can improve scalability. Most of these GNN-based methods, including the edge classification (EC) and the object condensation (OC) approach, require an input graph that needs to be constructed beforehand. In this work, we consider a one-shot OC approach that reconstructs particle tracks directly from a set of hits (point cloud) by recursively applying graph attention networks with an evolving graph structure. This approach iteratively updates the graphs and can better facilitate the message passing across each graph. Preliminary studies on the TrackML dataset show better track performance compared to the methods that require a fixed input graph.