English

Stacked Graph Filter

Machine Learning 2020-11-24 v1

Abstract

We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients. We find that by stacking graph filters with learnable polynomial parameters, we can build a highly adaptive and robust vertex classification model. Our treatment here relaxes the low-frequency (or equivalently, high homophily) assumptions in existing vertex classification models, resulting a more ubiquitous solution in terms of spectral properties. Empirically, by using only one hyper-parameter setting, our model achieves strong results on most benchmark datasets across the frequency spectrum.

Keywords

Cite

@article{arxiv.2011.10988,
  title  = {Stacked Graph Filter},
  author = {Hoang NT and Takanori Maehara and Tsuyoshi Murata},
  journal= {arXiv preprint arXiv:2011.10988},
  year   = {2020}
}

Comments

Source code is provided at github.com/gear/sgf