English

Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics

Machine Learning 2024-06-06 v2 High Energy Physics - Experiment

Abstract

This study introduces a novel transformer model optimized for large-scale point cloud processing in scientific domains such as high-energy physics (HEP) and astrophysics. Addressing the limitations of graph neural networks and standard transformers, our model integrates local inductive bias and achieves near-linear complexity with hardware-friendly regular operations. One contribution of this work is the quantitative analysis of the error-complexity tradeoff of various sparsification techniques for building efficient transformers. Our findings highlight the superiority of using locality-sensitive hashing (LSH), especially OR & AND-construction LSH, in kernel approximation for large-scale point cloud data with local inductive bias. Based on this finding, we propose LSH-based Efficient Point Transformer (HEPT), which combines E2^2LSH with OR & AND constructions and is built upon regular computations. HEPT demonstrates remarkable performance on two critical yet time-consuming HEP tasks, significantly outperforming existing GNNs and transformers in accuracy and computational speed, marking a significant advancement in geometric deep learning and large-scale scientific data processing. Our code is available at https://github.com/Graph-COM/HEPT.

Keywords

Cite

@article{arxiv.2402.12535,
  title  = {Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics},
  author = {Siqi Miao and Zhiyuan Lu and Mia Liu and Javier Duarte and Pan Li},
  journal= {arXiv preprint arXiv:2402.12535},
  year   = {2024}
}

Comments

Accepted to ICML 2024 (Oral)

R2 v1 2026-06-28T14:53:46.595Z