GLAudio Listens to the Sound of the Graph

TL;DR

GLAudio introduces a novel graph neural network architecture that propagates node features via the wave equation and then applies sequence learning, offering a new paradigm for processing graph-structured audio data.

Contribution

The paper presents GLAudio, a new graph learning architecture that separates information propagation and processing, with theoretical analysis of its expressivity and robustness.

Findings

The model's receptive field is characterized theoretically.

GLAudio demonstrates resilience against over-smoothing and over-squashing.

Experimental results validate the effectiveness on various graph datasets.

Abstract

We propose GLAudio: Graph Learning on Audio representation of the node features and the connectivity structure. This novel architecture propagates the node features through the graph network according to the discrete wave equation and then employs a sequence learning architecture to learn the target node function from the audio wave signal. This leads to a new paradigm of learning on graph-structured data, in which information propagation and information processing are separated into two distinct steps. We theoretically characterize the expressivity of our model, introducing the notion of the receptive field of a vertex, and investigate our model's susceptibility to over-smoothing and over-squashing both theoretically as well as experimentally on various graph datasets.