Accelerated GNN Tracking

The tracking of charged particles produced in collisions at colliders is a crucial aspect of the science program in the experiments. One of the primary challenges for the HL-LHC is the ability to efficiently, accurately, and rapidly perform tracking in collision events with large interaction pile-up. This project aims to improve charged-particle tracking in the ATLAS and CMS experiments through the use of Geometric Deep Learn methods (particularly Graph Neural Networks (GNNs)) and hardware-based acceleration (currently focused on FPGAs). —

Most current GNN-based approaches to tracking proceed in three distinct stages: graphs are constructed from point cloud of hits in the tracker, the graphs are processed through a GNN to predict a score for each edge (high scores indicate that the edge like belongs to a true particle track, low scores indicate it is a spurious or noise edge), and finally a clustering or graph walk algorithm is used to group the high-scored edges into track candidates. We are studying innovations and optimizations at all three stages of this pipeline. We are also exploring alternate ‘one-shot’ architectures that are trainable end-to-end and go from point-clouds to track candidates with fit parameters in a single pass.

We are also studying two complimentary approaches to accelerate the inference of these GNN tracking pipelines on FPGAs with the goal of assessing feasibility of these algorithms for use at the trigger level at the HL-LHC.. The first uses the OpenCL Framework to optimize a co-processor approach where kernels are initiated on a CPU and executed on the FPGA. The second uses the hls4ml package to translate different components of the GNN pipeline directly into FPGA firmware code.

Team

• Markus Atkinson
• Gage DeZoort
• Javier Duarte
• Abdelrahman Elabd
• Lindsey Gray
• Aneesh Heintz
• Jonathan Kutasov
• Mark Neubauer
• Isobel Ojalvo
• Caitlin Patterson
• Vesal Razavimaleki
• Savannah Thais
• Emily Tsai
• Bei Wang
• Kilian Lieret

Publications

• High Pileup Particle Tracking with Object Condensation, Kilian Lieret, Gage DeZoort, Devdoot Chatterjee, Jian Park, et.al. High Pileup Particle Tracking with Object Condensation. Submitted to 8th International Connecting The Dots Workshop (Toulouse 2023) (06 Dec 2023).
• An Object Condensation Pipeline for Charged Particle Tracking, Kilian Lieret and Gage DeZoort. An Object Condensation Pipeline for Charged Particle Tracking. Submitted to 8th International Connecting The Dots Workshop (Toulouse 2023) (28 Sep 2023).
• Equivariant Graph Neural Networks for Charged Particle Tracking, D. Murnane, S. Thais and A. Thete, arXiv 2304.05293 (11 Apr 2023) [9 citations].
• Physics Community Needs, Tools, and Resources for Machine Learning, P. Harris et. al., arXiv 2203.16255 (30 Mar 2022) [12 citations].
• Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges, S. Thais, P. Calafiura, G. Chachamis, G. DeZoort, J. Duarte, S. Ganguly, M. Kagan, D. Murnane, M. Neubauer and K. Terao, arXiv 2203.12852 (23 Mar 2022) [35 citations].
• Graph Segmentation in Scientific Datasets, R. Sahay and S. Thais, Graph Segmentation in Scientific Datasets, Submitted to the Machine Learning and the Physical Sciences workshop at NeurIPS 2021 (13 Dec 2021).
• Graph Neural Networks for Charged Particle Tracking on FPGAs, A. Elabd et. al., Front.Big Data 5 828666 (2022) (03 Dec 2021) [32 citations] [NSF PAR].
• Applications and Techniques for Fast Machine Learning in Science, A. Deiana et. al., Front.Big Data 5 787421 (2022) (25 Oct 2021) [37 citations] [NSF PAR].
• Particle Cloud Generation with Message Passing Generative Adversarial Networks, R. Kansal, J. Duarte, H. Su, B. Orzari, T. Tomei, M. Pierini, M. Touranakou, J. Vlimant and D. Gunopulos, arXiv 2106.11535 (22 Jun 2021) [50 citations].
• Charged Particle Tracking via Edge-Classifying Interaction Networks, G. DeZoort, S. Thais, J. Duarte, V. Razavimaleki, M. Atkinson, I. Ojalvo, M. Neubauer and P. Elmer, Comput.Softw.Big Sci. 5 26 (2021) (30 Mar 2021) [45 citations] [NSF PAR].
• Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC, S. Thais and G. DeZoort, arXiv 2103.06509 (21 Mar 2021) [6 citations].
• Performance of a geometric deep learning pipeline for HL-LHC particle tracking, X. Ju et. al., Eur.Phys.J.C 81 876 (2021) (11 Mar 2021) [61 citations] [NSF PAR].
• Accelerated Charged Particle Tracking with Graph Neural Networks on FPGAs, A. Heintz et. al., arXiv 2012.01563 (30 Nov 2020) [26 citations].

Recent recordings