Stacked Graph Filter
arXiv:2011.10988
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.
arXiv commentSource code is provided at github.com/gear/sgf
References in corpus (16)
- Semi-Supervised Classification with Graph Convolutional Networks
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Inductive Representation Learning on Large Graphs
- Adversarial Attacks on Neural Networks for Graph Data
- Representation Learning on Graphs with Jumping Knowledge Networks
- Pitfalls of Graph Neural Network Evaluation
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Graph Neural Networks with convolutional ARMA filters
- Simple and Deep Graph Convolutional Networks
- Adversarial Attacks on Graph Neural Networks via Meta Learning
- Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
- LanczosNet: Multi-Scale Deep Graph Convolutional Networks
- Adversarial Attacks on Node Embeddings via Graph Poisoning
- Adversarial Attack on Graph Structured Data
- Adaptive Propagation Graph Convolutional Network
- Non-Local Graph Neural Networks