Message Passing in Graph Convolution Networks via Adaptive Filter Banks

Abstract

Graph convolution networks, like message passing graph convolution networks (MPGCNs), have been a powerful tool in representation learning of networked data. However, when data is heterogeneous, most architectures are limited as they employ a single strategy to handle multi-channel graph signals and they typically focus on low-frequency information. In this paper, we present a novel graph convolution operator, termed BankGCN, which keeps benefits of message passing models, but extends their capabilities beyond `low-pass' features. It decomposes multi-channel signals on graphs into subspaces and handles particular information in each subspace with an adapted filter. The filters of all subspaces have different frequency responses and together form a filter bank. Furthermore, each filter in the spectral domain corresponds to a message passing scheme, and diverse schemes are implemented via the filter bank. Importantly, the filter bank and the signal decomposition are jointly learned to adapt to the spectral characteristics of data and to target applications. Furthermore, this is implemented almost without extra parameters in comparison with most existing MPGCNs. Experimental results show that the proposed convolution operator permits to achieve excellent performance in graph classification on a collection of benchmark graph datasets.

References in corpus (15)

• 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
• Neural Message Passing for Quantum Chemistry
• Fast Graph Representation Learning with PyTorch Geometric
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Graph Neural Networks with convolutional ARMA filters
• Perfect Reconstruction Two-Channel Wavelet Filter-Banks for Graph Structured Data
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Principal Neighbourhood Aggregation for Graph Nets
• Benchmarking Graph Neural Networks
• Compact Support Biorthogonal Wavelet Filterbanks for Arbitrary Undirected Graphs
• Learning parametric dictionaries for graph signals
• Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
• Graph-based Isometry Invariant Representation Learning