Saved in:
Bibliographic Details
Main Authors: Miao, Siqi, Lu, Zhiyuan, Liu, Mia, Duarte, Javier, Li, Pan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.12535
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916275479904256
author Miao, Siqi
Lu, Zhiyuan
Liu, Mia
Duarte, Javier
Li, Pan
author_facet Miao, Siqi
Lu, Zhiyuan
Liu, Mia
Duarte, Javier
Li, Pan
contents 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 E$^2$LSH 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_12535
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
Miao, Siqi
Lu, Zhiyuan
Liu, Mia
Duarte, Javier
Li, Pan
Machine Learning
High Energy Physics - Experiment
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 E$^2$LSH 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.
title Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics
topic Machine Learning
High Energy Physics - Experiment
url https://arxiv.org/abs/2402.12535