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

1 code implementation • 19 Feb 2024 • Siqi Miao, Zhiyuan Lu, Mia Liu, Javier Duarte, Pan Li

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.

Inductive Bias

High Pileup Particle Tracking with Object Condensation

1 code implementation • 6 Dec 2023 • Kilian Lieret, Gage DeZoort, Devdoot Chatterjee, Jian Park, Siqi Miao, Pan Li

Recent work has demonstrated that graph neural networks (GNNs) can match the performance of traditional algorithms for charged particle tracking while improving scalability to meet the computing challenges posed by the HL-LHC.

Edge Classification Object

GDL-DS: A Benchmark for Geometric Deep Learning under Distribution Shifts

1 code implementation • 12 Oct 2023 • Deyu Zou, Shikun Liu, Siqi Miao, Victor Fung, Shiyu Chang, Pan Li

Geometric deep learning (GDL) has gained significant attention in various scientific fields, chiefly for its proficiency in modeling data with intricate geometric structures.

Interpretable Geometric Deep Learning via Learnable Randomness Injection

1 code implementation • 30 Oct 2022 • Siqi Miao, Yunan Luo, Mia Liu, Pan Li

LRI-induced models, once trained, can detect the points in the point cloud data that carry information indicative of the prediction label.

Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism

2 code implementations • 31 Jan 2022 • Siqi Miao, Miaoyuan Liu, Pan Li

However, those post-hoc methods often fail to provide stable interpretation and may extract features that are spuriously correlated with the task.

Graph Learning