Adaptive Filters in Graph Convolutional Neural Networks

TL;DR

This paper introduces a novel method for spatial convolution in Graph Neural Networks that dynamically generates input-specific filters from node features, enhancing adaptability and performance on graph-structured data.

Contribution

It proposes a new approach to adapt ConvGNNs with input-specific, dynamically generated filters, improving flexibility and efficiency in processing graph data.

Findings

Achieves satisfying results with a low number of filters.

Demonstrates the effectiveness of input-specific filters in spatial convolution.

Enhances adaptability of ConvGNNs to diverse graph structures.

Abstract

Over the last few years, we have witnessed the availability of an increasing data generated from non-Euclidean domains, which are usually represented as graphs with complex relationships, and Graph Neural Networks (GNN) have gained a high interest because of their potential in processing graph-structured data. In particular, there is a strong interest in exploring the possibilities in performing convolution on graphs using an extension of the GNN architecture, generally referred to as Graph Convolutional Neural Networks (ConvGNN). Convolution on graphs has been achieved mainly in two forms: spectral and spatial convolutions. Due to the higher flexibility in exploring and exploiting the graph structure of data, there is recently an increasing interest in investigating the possibilities that the spatial approach can offer. The idea of finding a way to adapt the network behaviour to the inputs they process to maximize the total performances has aroused much interest in the neural networks literature over the years. This paper presents a novel method to adapt the behaviour of a ConvGNN to the input proposing a method to perform spatial convolution on graphs using input-specific filters, which are dynamically generated from nodes feature vectors. The experimental assessment confirms the capabilities of the proposed approach, which achieves satisfying results using a low number of filters.