IV-GNN : Interval Valued Data Handling Using Graph Neural Network

TL;DR

This paper introduces IV-GNN, a novel graph neural network capable of handling interval-valued node features, expanding GNN applicability to non-Euclidean data with interval uncertainties.

Contribution

The paper proposes a new GNN model that processes interval-valued features, relaxing the restriction to countable feature spaces and demonstrating its effectiveness for graph classification.

Findings

IV-GNN outperforms state-of-the-art models on benchmark datasets.

The new aggregation scheme effectively captures diverse interval structures.

Theoretical analysis confirms the model's expressive power.

Abstract

Graph Neural Network (GNN) is a powerful tool to perform standard machine learning on graphs. To have a Euclidean representation of every node in the Non-Euclidean graph-like data, GNN follows neighbourhood aggregation and combination of information recursively along the edges of the graph. Despite having many GNN variants in the literature, no model can deal with graphs having nodes with interval-valued features. This article proposes an Interval-ValuedGraph Neural Network, a novel GNN model where, for the first time, we relax the restriction of the feature space being countable. Our model is much more general than existing models as any countable set is always a subset of the universal set $R^{n}$, which is uncountable. Here, to deal with interval-valued feature vectors, we propose a new aggregation scheme of intervals and show its expressive power to capture different interval structures. We validate our theoretical findings about our model for graph classification tasks by comparing its performance with those of the state-of-the-art models on several benchmark network and synthetic datasets.