Locality-sensitive Hashing-based Efficient Point Transformer With Applications In High-energy Physics

Miao Siqi, Lu Zhiyuan, Liu Mia, Duarte Javier, Li Pan. Arxiv 2024

[Paper] [Code]    
ARXIV Deep Learning Graph Has Code LSH Supervised

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.

Similar Work

• Vision Transformer Hashing For Image Retrieval
• Transhash Transformer-based Hamming Hashing For Efficient Image Retrieval
• Hashformers Towards Vocabulary-independent Pre-trained Transformers
• Efficient Bitmap-based Indexing And Retrieval Of Similarity Search Image Queries