K-Plex Cover Pooling for Graph Neural Networks
Abstract
We introduce a novel pooling technique which borrows from classical results in graph theory that is non-parametric and generalizes well to graphs of different nature and connectivity pattern. Our pooling method, named KPlexPool, builds on the concepts of graph covers and $k$-plexes, i.e. pseudo-cliques where each node can miss up to $k$ links. The experimental evaluation on molecular and social graph classification shows that KPlexPool achieves state of the art performances, supporting the intuition that well-founded graph-theoretic approaches can be effectively integrated in learning models for graphs.
Cite
Text
Bacciu et al. "K-Plex Cover Pooling for Graph Neural Networks." NeurIPS 2020 Workshops: LMCA, 2020.Markdown
[Bacciu et al. "K-Plex Cover Pooling for Graph Neural Networks." NeurIPS 2020 Workshops: LMCA, 2020.](https://mlanthology.org/neuripsw/2020/bacciu2020neuripsw-kplex/)BibTeX
@inproceedings{bacciu2020neuripsw-kplex,
title = {{K-Plex Cover Pooling for Graph Neural Networks}},
author = {Bacciu, Davide and Conte, Alessio and Grossi, Roberto and Landolfi, Francesco and Marino, Andrea},
booktitle = {NeurIPS 2020 Workshops: LMCA},
year = {2020},
url = {https://mlanthology.org/neuripsw/2020/bacciu2020neuripsw-kplex/}
}