BLIS-Net: Classifying and Analyzing Signals on Graphs
It addresses signal classification on graphs, a less explored task compared to node or graph classification, with incremental improvements over existing geometric scattering methods.
The paper tackles the problem of signal classification on graphs, where traditional GNNs are inadequate due to their reliance on localized low-pass filters, and introduces BLIS-Net, a novel GNN that captures both local and global signal structure with low- and high-frequency information, achieving superior performance on synthetic and real-world datasets like traffic flow and fMRI data.
Graph neural networks (GNNs) have emerged as a powerful tool for tasks such as node classification and graph classification. However, much less work has been done on signal classification, where the data consists of many functions (referred to as signals) defined on the vertices of a single graph. These tasks require networks designed differently from those designed for traditional GNN tasks. Indeed, traditional GNNs rely on localized low-pass filters, and signals of interest may have intricate multi-frequency behavior and exhibit long range interactions. This motivates us to introduce the BLIS-Net (Bi-Lipschitz Scattering Net), a novel GNN that builds on the previously introduced geometric scattering transform. Our network is able to capture both local and global signal structure and is able to capture both low-frequency and high-frequency information. We make several crucial changes to the original geometric scattering architecture which we prove increase the ability of our network to capture information about the input signal and show that BLIS-Net achieves superior performance on both synthetic and real-world data sets based on traffic flow and fMRI data.