MaxCutPool: Differentiable Feature-Aware Maxcut for Pooling in Graph Neural Networks
Abstract
We propose a novel approach to compute the MAXCUT in attributed graphs, i.e., graphs with features associated with nodes and edges. Our approach works well on any kind of graph topology and can find solutions that jointly optimize the MAXCUT along with other objectives. Based on the obtained MAXCUT partition, we implement a hierarchical graph pooling layer for Graph Neural Networks, which is sparse, trainable end-to-end, and particularly suitable for downstream tasks on heterophilic graphs.
Cite
Text
Abate and Bianchi. "MaxCutPool: Differentiable Feature-Aware Maxcut for Pooling in Graph Neural Networks." International Conference on Learning Representations, 2025.Markdown
[Abate and Bianchi. "MaxCutPool: Differentiable Feature-Aware Maxcut for Pooling in Graph Neural Networks." International Conference on Learning Representations, 2025.](https://mlanthology.org/iclr/2025/abate2025iclr-maxcutpool/)BibTeX
@inproceedings{abate2025iclr-maxcutpool,
title = {{MaxCutPool: Differentiable Feature-Aware Maxcut for Pooling in Graph Neural Networks}},
author = {Abate, Carlo and Bianchi, Filippo Maria},
booktitle = {International Conference on Learning Representations},
year = {2025},
url = {https://mlanthology.org/iclr/2025/abate2025iclr-maxcutpool/}
}