GRAFENNE: Learning on Graphs with Heterogeneous and Dynamic Feature Sets

TL;DR

GRAFENNE introduces a novel graph neural network framework that effectively handles heterogeneous and dynamic feature sets by decoupling nodes and features, enabling inductive learning and maintaining high expressivity.

Contribution

The paper proposes GRAFENNE, a new GNN framework that addresses limitations of existing methods by supporting dynamic, heterogeneous features through an allotropic transformation and bipartite encoding.

Findings

GRAFENNE is as expressive as existing message-passing GNNs.

It is inductive to unseen nodes and features.

Demonstrated high empirical efficacy on real-world graphs.

Abstract

Graph neural networks (GNNs), in general, are built on the assumption of a static set of features characterizing each node in a graph. This assumption is often violated in practice. Existing methods partly address this issue through feature imputation. However, these techniques (i) assume uniformity of feature set across nodes, (ii) are transductive by nature, and (iii) fail to work when features are added or removed over time. In this work, we address these limitations through a novel GNN framework called GRAFENNE. GRAFENNE performs a novel allotropic transformation on the original graph, wherein the nodes and features are decoupled through a bipartite encoding. Through a carefully chosen message passing framework on the allotropic transformation, we make the model parameter size independent of the number of features and thereby inductive to both unseen nodes and features. We prove that GRAFENNE is at least as expressive as any of the existing message-passing GNNs in terms of Weisfeiler-Leman tests, and therefore, the additional inductivity to unseen features does not come at the cost of expressivity. In addition, as demonstrated over four real-world graphs, GRAFENNE empowers the underlying GNN with high empirical efficacy and the ability to learn in continual fashion over streaming feature sets.