# On Graph Classification Networks, Datasets and Baselines

arXiv: https://arxiv.org/abs/1905.04682 · HTML: https://mlsanity.com/paper/1905.04682/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2019.

## Built on by (most cited first, 8 of 8)

- [Expander Graph Propagation](https://mlsanity.com/paper/2210.02997/) (2022)
- [GraphWorld: Fake Graphs Bring Real Insights for GNNs](https://mlsanity.com/paper/2203.00112/) (2022)
- [From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers](https://mlsanity.com/paper/2107.07999/) (2021)
- [Graph Kernel Neural Networks](https://mlsanity.com/paper/2112.07436/) (2021)
- [Molecular Topological Profile (MOLTOP) -- Simple and Strong Baseline for Molecular Graph Classification](https://mlsanity.com/paper/2407.12136/) (2024)
- [Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification](https://mlsanity.com/paper/2111.11482/) (2021)
- [Lymph Node Graph Neural Networks for Cancer Metastasis Prediction](https://mlsanity.com/paper/2106.01711/) (2021)
- [Sparsifying the Update Step in Graph Neural Networks](https://mlsanity.com/paper/2109.00909/) (2021)

## Abstract (arXiv)

Graph classification receives a great deal of attention from the non-Euclidean machine learning community. Recent advances in graph coarsening have enabled the training of deeper networks and produced new state-of-the-art results in many benchmark tasks. We examine how these architectures train and find that performance is highly-sensitive to initialisation and depends strongly on jumping-knowledge structures. We then show that, despite the great complexity of these models, competitive performance is achieved by the simplest of models -- structure-blind MLP, single-layer GCN and fixed-weight GCN -- and propose these be included as baselines in future.