# A Graph Convolutional Network Composition Framework for Semi-supervised Classification

arXiv: https://arxiv.org/abs/2004.03994 · HTML: https://mlsanity.com/paper/2004.03994/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2020.

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

- [Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks](https://mlsanity.com/paper/2104.02153/) (2021)
- [Deep Manifold Learning with Graph Mining](https://mlsanity.com/paper/2207.08377/) (2022)

## Abstract (arXiv)

Graph convolutional networks (GCNs) have gained popularity due to high performance achievable on several downstream tasks including node classification. Several architectural variants of these networks have been proposed and investigated with experimental studies in the literature. Motivated by a recent work on simplifying GCNs, we study the problem of designing other variants and propose a framework to compose networks using building blocks of GCN. The framework offers flexibility to compose and evaluate different networks using feature and/or label propagation networks, linear or non-linear networks, with each composition having different computational complexity. We conduct a detailed experimental study on several benchmark datasets with many variants and present observations from our evaluation. Our empirical experimental results suggest that several newly composed variants are useful alternatives to consider because they are as competitive as, or better than the original GCN.