Higher-order Clustering and Pooling for Graph Neural Networks
Abstract
Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However, they are not only questioned by recent work showing on par performance with random pooling, but also ignore completely higher-order connectivity patterns. To tackle this issue, we propose HoscPool, a clustering-based graph pooling operator that captures higher-order information hierarchically, leading to richer graph representations. In fact, we learn a probabilistic cluster assignment matrix end-to-end by minimising relaxed formulations of motif spectral clustering in our objective function, and we then extend it to a pooling operator. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure, achieving best performance. Lastly, we provide a deep empirical analysis of pooling operators' inner functioning.
Cite
@article{arxiv.2209.03473,
title = {Higher-order Clustering and Pooling for Graph Neural Networks},
author = {Alexandre Duval and Fragkiskos Malliaros},
journal= {arXiv preprint arXiv:2209.03473},
year = {2022}
}
Comments
CIKM 2022