Scaling Up Graph Neural Networks Via Graph Coarsening

Huang, Zengfeng; Zhang, Shengzhong; Xi, Chong; Zhou, Min

doi:10.48550/arxiv.2106.05150

Cited by 1 publication

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph coarsening strategies for reducing computation must strike a balance by sacrificing the accuracy of segmentation [8]. Achieving an optimum coarseness for downsampling is a hard task, since it depends heavily on the dataset and the scale of the objects that we wish to segment.…”

Section: Introductionmentioning

confidence: 99%

HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud Processing

Thieshanthan¹,

Niwarthana²,

Somarathne³

et al. 2022

Preprint

View full text Add to dashboard Cite

Inspired by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing and feature learning over large-scale outdoor LiDAR point clouds. We observe that existing GNN based methods fail to overcome challenges of scale and irregularity of points in outdoor datasets. Addressing the need to preserve structural details while learning over a larger volume efficiently, we propose Hierarchical Point Graph Neural Network (HPGNN). It learns node features at various levels of graph coarseness to extract information. This enables to learn over a large point cloud while retaining fine details that existing pointlevel graph networks struggle to achieve. Connections between multiple levels enable a point to learn features in multiple scales, in a few iterations. We design HPGNN as a purely GNN-based approach, so that it offers modular expandability as seen with other point-based and Graph network baselines. To illustrate the improved processing capability, we compare previous point based and GNN models for semantic segmentation with our HPGNN, achieving a significant improvement for GNNs (+36.7 mIoU) on the SemanticKITTI dataset.

show abstract

Section: Introductionmentioning

confidence: 99%