paper-with-me

Papers

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

2024-02-19 · Siqi Miao, Zhiyuan Lu, Mia Liu, Javier Duarte, Pan Li

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.

📄 PDF Abstract BibTeX arXiv:2402.12535

Code (1)

graph-com/hept 공식 구현 pytorch

Tasks

Inductive Bias

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Application of Structured State Space Models to High energy physics with locality-sensitive hashing

2025-01-27 · Cheng Jiang, Sitian Qian

Modern high-energy physics (HEP) experiments are increasingly challenged by the vast size and complexity of their datasets, particularly regarding large-scale point cloud processing and long sequences. In this study, to …

Inductive BiasMambaState Space Models

Efficient Bitmap-based Indexing and Retrieval of Similarity Search Image Queries

2019-12-15 · Omid Jafari, Parth Nagarkar, Jonathan Montaño

Finding similar images is a necessary operation in many multimedia applications. Images are often represented and stored as a set of high-dimensional features, which are extracted using localized feature extraction algor…

Retrieval

Experimental Analysis of Machine Learning Techniques for Finding Search Radius in Locality Sensitive Hashing

2022-11-16 · Omid Jafari, Parth Nagarkar

Finding similar data in high-dimensional spaces is one of the important tasks in multimedia applications. Approaches introduced to find exact searching techniques often use tree-based index structures which are known to …

LAHNet: Local Attentive Hashing Network for Point Cloud Registration

2025-11-30 · Wentao Qu, Xiaoshui Huang, Liang Xiao arxiv

Most existing learning-based point cloud descriptors for point cloud registration focus on perceiving local information of point clouds to generate distinctive features. However, a reasonable and broader receptive field …

Point Cloud RegistrationPoint Clouds

Falconn++: A Locality-sensitive Filtering Approach for Approximate Nearest Neighbor Search

2022-06-03 · Ninh Pham, Tao Liu

We present Falconn++, a novel locality-sensitive filtering approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket \textit{before} query…