# When Work Matters: Transforming Classical Network Structures to Graph CNN

arXiv: https://arxiv.org/abs/1807.02653 · HTML: https://mlsanity.com/paper/1807.02653/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2018.

## Built on by (most cited first, 6 of 6)

- [Revisiting 2D Convolutional Neural Networks for Graph-based Applications](https://mlsanity.com/paper/2105.11016/) (2021)
- [Quadratic GCN for Graph Classification](https://mlsanity.com/paper/2104.06750/) (2021)
- [Boosting Graph Neural Networks by Injecting Pooling in Message Passing](https://mlsanity.com/paper/2202.04768/) (2022)
- [Extracting real estate values of rental apartment floor plans using graph convolutional networks](https://mlsanity.com/paper/2303.13568/) (2023)
- [Graph in Graph Neural Network](https://mlsanity.com/paper/2407.00696/) (2024)
- [An Unsupervised Learning Framework Combined with Heuristics for the Maximum Minimal Cut Problem](https://mlsanity.com/paper/2408.08484/) (2024)

## Abstract (arXiv)

Numerous pattern recognition applications can be formed as learning from graph-structured data, including social network, protein-interaction network, the world wide web data, knowledge graph, etc. While convolutional neural network (CNN) facilitates great advances in gridded image/video understanding tasks, very limited attention has been devoted to transform these successful network structures (including Inception net, Residual net, Dense net, etc.) to establish convolutional networks on graph, due to its irregularity and complexity geometric topologies (unordered vertices, unfixed number of adjacent edges/vertices). In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem. Specifically, we firstly review the general graph CNN methods, especially in its spectral filtering operation on the irregular graph data. We then introduce the basic structures of ResNet, Inception and DenseNet into graph CNN and construct these network structures on graph, named as G_ResNet, G_Inception, G_DenseNet. In particular, it seeks to help graph CNNs by shedding light on how these classical network structures work and providing guidelines for choosing appropriate graph network frameworks. Finally, we comprehensively evaluate the performance of these different network structures on several public graph datasets (including social networks and bioinformatic datasets), and demonstrate how different network structures work on graph CNN in the graph recognition task.