# Clique pooling for graph classification

arXiv: https://arxiv.org/abs/1904.00374 · HTML: https://mlsanity.com/paper/1904.00374/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2019.

## Built on by (most cited first, 13 of 13)

- [Understanding Pooling in Graph Neural Networks](https://mlsanity.com/paper/2110.05292/) (2021)
- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [Higher-order Clustering and Pooling for Graph Neural Networks](https://mlsanity.com/paper/2209.03473/) (2022)
- [MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations](https://mlsanity.com/paper/2211.00713/) (2022)
- [Over-Squashing in Graph Neural Networks: A Comprehensive survey](https://mlsanity.com/paper/2308.15568/) (2023)
- [Structure-Aware Hierarchical Graph Pooling using Information Bottleneck](https://mlsanity.com/paper/2104.13012/) (2021)
- [Generalizing Downsampling from Regular Data to Graphs](https://mlsanity.com/paper/2208.03523/) (2022)
- [Clustering for Protein Representation Learning](https://mlsanity.com/paper/2404.00254/) (2024)
- [Curvature-based Pooling within Graph Neural Networks](https://mlsanity.com/paper/2308.16516/) (2023)
- [MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks](https://mlsanity.com/paper/2409.05100/) (2024)
- [Renormalized Graph Representations for Node Classification](https://mlsanity.com/paper/2306.00707/) (2023)
- [Quadratic GCN for Graph Classification](https://mlsanity.com/paper/2104.06750/) (2021)
- [NervePool: A Simplicial Pooling Layer](https://mlsanity.com/paper/2305.06315/) (2023)

## Abstract (arXiv)

We propose a novel graph pooling operation using cliques as the unit pool. As this approach is purely topological, rather than featural, it is more readily interpretable, a better analogue to image coarsening than filtering or pruning techniques, and entirely nonparametric. The operation is implemented within graph convolution network (GCN) and GraphSAGE architectures and tested against standard graph classification benchmarks. In addition, we explore the backwards compatibility of the pooling to regular graphs, demonstrating competitive performance when replacing two-by-two pooling in standard convolutional neural networks (CNNs) with our mechanism.