# Graph Structure from Point Clouds: Geometric Attention is All You Need

arXiv: https://arxiv.org/abs/2307.16662 · HTML: https://mlsanity.com/paper/2307.16662/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 31 Jul 2023.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [Particle Transformer for Jet Tagging](https://mlsanity.com/paper/2202.03772/) (2022)
- [Energy Flow Networks: Deep Sets for Particle Jets](https://mlsanity.com/paper/1810.05165/) (2018)
- [Learning representations of irregular particle-detector geometry with distance-weighted graph networks](https://mlsanity.com/paper/1902.07987/) (2019)
- [MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks](https://mlsanity.com/paper/2101.08578/) (2021)
- [Distance-Weighted Graph Neural Networks on FPGAs for Real-Time Particle Reconstruction in High Energy Physics](https://mlsanity.com/paper/2008.03601/) (2020)
- [Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking](https://mlsanity.com/paper/2103.06995/) (2021)
- [Point Attention Network for Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/1909.12663/) (2019)
- [Explaining machine-learned particle-flow reconstruction](https://mlsanity.com/paper/2111.12840/) (2021)
- [Investigating Attention Mechanism in 3D Point Cloud Object Detection](https://mlsanity.com/paper/2108.00620/) (2021)
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://mlsanity.com/paper/2102.10788/) (2021)
- [End-to-end multi-particle reconstruction in high occupancy imaging calorimeters with graph neural networks](https://mlsanity.com/paper/2204.01681/) (2022)

## Built on by (most cited first, 2 of 2)

- [SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention](https://mlsanity.com/paper/2308.03718/) (2023)
- [Jet Discrimination with Quantum Complete Graph Neural Network](https://mlsanity.com/paper/2403.04990/) (2024)

## Abstract (arXiv)

The use of graph neural networks has produced significant advances in point cloud problems, such as those found in high energy physics. The question of how to produce a graph structure in these problems is usually treated as a matter of heuristics, employing fully connected graphs or K-nearest neighbors. In this work, we elevate this question to utmost importance as the Topology Problem. We propose an attention mechanism that allows a graph to be constructed in a learned space that handles geometrically the flow of relevance, providing one solution to the Topology Problem. We test this architecture, called GravNetNorm, on the task of top jet tagging, and show that it is competitive in tagging accuracy, and uses far fewer computational resources than all other comparable models.