GTAGCN: Generalized Topology Adaptive Graph Convolutional Networks

TL;DR

GTAGCN introduces a hybrid graph neural network approach that adaptively combines topology and aggregation techniques, effectively handling both sequenced and static graph data for classification tasks.

Contribution

The paper proposes a novel hybrid GNN model combining generalized aggregation and topology adaptive convolution, applicable to both node and graph classification for diverse data types.

Findings

Performs comparably to existing methods on standard benchmarks.

Achieves superior results on handwritten stroke data.

Demonstrates versatility across sequenced and static data.

Abstract

Graph Neural Networks (GNN) have emerged as a popular and standard approach for learning from graph-structured data. The literature on GNN highlights the potential of this evolving research area and its widespread adoption in real-life applications. However, most of the approaches are either new in concept or derived from specific techniques. Therefore, the potential of more than one approach in hybrid form has not been studied extensively, which can be well utilized for sequenced data or static data together. We derive a hybrid approach based on two established techniques as generalized aggregation networks and topology adaptive graph convolution networks that solve our purpose to apply on both types of sequenced and static nature of data, effectively. The proposed method applies to both node and graph classification. Our empirical analysis reveals that the results are at par with literature results and better for handwritten strokes as sequenced data, where graph structures have not been explored.