# Low Latency Edge Classification GNN for Particle Trajectory Tracking on FPGAs

arXiv: https://arxiv.org/abs/2306.11330 · HTML: https://mlsanity.com/paper/2306.11330/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 20 Jun 2023.

## Builds on (most cited first, 11 of 11)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Fast inference of deep neural networks in FPGAs for particle physics](https://mlsanity.com/paper/1804.06913/) (2018)
- [HyGCN: A GCN Accelerator with Hybrid Architecture](https://mlsanity.com/paper/2001.02514/) (2020)
- [EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks](https://mlsanity.com/paper/1909.00155/) (2019)
- [GRIP: A Graph Neural Network Accelerator Architecture](https://mlsanity.com/paper/2007.13828/) (2020)
- [MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks](https://mlsanity.com/paper/2101.08578/) (2021)
- [Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs](https://mlsanity.com/paper/2012.01563/) (2020)
- [Charged particle tracking via edge-classifying interaction networks](https://mlsanity.com/paper/2103.16701/) (2021)
- [Graph Neural Networks for Charged Particle Tracking on FPGAs](https://mlsanity.com/paper/2112.02048/) (2021)

## Built on by (most cited first, 1 of 1)

- [Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence](https://mlsanity.com/paper/2407.15320/) (2024)

## Abstract (arXiv)

In-time particle trajectory reconstruction in the Large Hadron Collider is challenging due to the high collision rate and numerous particle hits. Using GNN (Graph Neural Network) on FPGA has enabled superior accuracy with flexible trajectory classification. However, existing GNN architectures have inefficient resource usage and insufficient parallelism for edge classification. This paper introduces a resource-efficient GNN architecture on FPGAs for low latency particle tracking. The modular architecture facilitates design scalability to support large graphs. Leveraging the geometric properties of hit detectors further reduces graph complexity and resource usage. Our results on Xilinx UltraScale+ VU9P demonstrate 1625x and 1574x performance improvement over CPU and GPU respectively.