# A Multiscale Graph Convolutional Network Using Hierarchical Clustering

arXiv: https://arxiv.org/abs/2006.12542 · HTML: https://mlsanity.com/paper/2006.12542/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [Learning Hierarchical Graph Neural Networks for Image Clustering](https://mlsanity.com/paper/2107.01319/) (2021)
- [Renormalized Graph Representations for Node Classification](https://mlsanity.com/paper/2306.00707/) (2023)
- [Attributed Graph Clustering with Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning](https://mlsanity.com/paper/2507.20505/) (2025)

## Abstract (arXiv)

The information contained in hierarchical topology, intrinsic to many networks, is currently underutilised. A novel architecture is explored which exploits this information through a multiscale decomposition. A dendrogram is produced by a Girvan-Newman hierarchical clustering algorithm. It is segmented and fed through graph convolutional layers, allowing the architecture to learn multiple scale latent space representations of the network, from fine to coarse grained. The architecture is tested on a benchmark citation network, demonstrating competitive performance. Given the abundance of hierarchical networks, possible applications include quantum molecular property prediction, protein interface prediction and multiscale computational substrates for partial differential equations.