Graph Neural Networks with convolutional ARMA filters
This work addresses the need for more flexible and robust graph neural networks for researchers and practitioners in graph-based machine learning, though it is incremental as it builds on existing spectral filter approaches.
The authors tackled the problem of graph neural networks using polynomial spectral filters by proposing a novel graph convolutional layer based on ARMA filters, which resulted in significant improvements in tasks like semi-supervised node classification, graph signal classification, graph classification, and graph regression compared to existing polynomial-based methods.
Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters. In this paper, we propose a novel graph convolutional layer inspired by the auto-regressive moving average (ARMA) filter that, compared to polynomial ones, provides a more flexible frequency response, is more robust to noise, and better captures the global graph structure. We propose a graph neural network implementation of the ARMA filter with a recursive and distributed formulation, obtaining a convolutional layer that is efficient to train, localized in the node space, and can be transferred to new graphs at test time. We perform a spectral analysis to study the filtering effect of the proposed ARMA layer and report experiments on four downstream tasks: semi-supervised node classification, graph signal classification, graph classification, and graph regression. Results show that the proposed ARMA layer brings significant improvements over graph neural networks based on polynomial filters.