# Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification

arXiv: https://arxiv.org/abs/2108.06317 · HTML: https://mlsanity.com/paper/2108.06317/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 13 Aug 2021.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [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)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Joint 2D-3D-Semantic Data for Indoor Scene Understanding](https://mlsanity.com/paper/1702.01105/) (2017)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Kernel Operations on the GPU, with Autodiff, without Memory Overflows](https://mlsanity.com/paper/2004.11127/) (2020)
- [Degree-Quant: Quantization-Aware Training for Graph Neural Networks](https://mlsanity.com/paper/2008.05000/) (2020)
- [A Closer Look at Local Aggregation Operators in Point Cloud Analysis](https://mlsanity.com/paper/2007.01294/) (2020)
- [BiPointNet: Binary Neural Network for Point Clouds](https://mlsanity.com/paper/2010.05501/) (2020)
- [View-volume Network for Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1806.05361/) (2018)

## Built on by (most cited first, 9 of 9)

- [Mind the Label Shift of Augmentation-based Graph OOD Generalization](https://mlsanity.com/paper/2303.14859/) (2023)
- [Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis](https://mlsanity.com/paper/2205.09702/) (2022)
- [Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms](https://mlsanity.com/paper/2303.10875/) (2023)
- [Decoupled Local Aggregation for Point Cloud Learning](https://mlsanity.com/paper/2308.16532/) (2023)
- [LMSeg: An end-to-end geometric message-passing network on barycentric dual graphs for large-scale landscape mesh segmentation](https://mlsanity.com/paper/2407.04326/) (2024)
- [Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network](https://mlsanity.com/paper/2407.04334/) (2024)
- [HGNAS: Hardware-Aware Graph Neural Architecture Search for Edge Devices](https://mlsanity.com/paper/2408.12840/) (2024)
- [GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search](https://mlsanity.com/paper/2512.11856/) (2025)
- [Rotation-Invariant Multi-IMU Activity Recognition under Independent Per-Location Orientation Shifts](https://mlsanity.com/paper/2608.15621/) (2026)

## Abstract (arXiv)

In recent years graph neural network (GNN)-based approaches have become a popular strategy for processing point cloud data, regularly achieving state-of-the-art performance on a variety of tasks. To date, the research community has primarily focused on improving model expressiveness, with secondary thought given to how to design models that can run efficiently on resource constrained mobile devices including smartphones or mixed reality headsets. In this work we make a step towards improving the efficiency of these models by making the observation that these GNN models are heavily limited by the representational power of their first, feature extracting, layer. We find that it is possible to radically simplify these models so long as the feature extraction layer is retained with minimal degradation to model performance; further, we discover that it is possible to improve performance overall on ModelNet40 and S3DIS by improving the design of the feature extractor. Our approach reduces memory consumption by 20× and latency by up to 9.9× for graph layers in models such as DGCNN; overall, we achieve speed-ups of up to 4.5× and peak memory reductions of 72.5%.