Relating-Up: Advancing Graph Neural Networks through Inter-Graph Relationships

TL;DR

This paper introduces Relating-Up, a modular enhancement for GNNs that captures inter-graph relationships through a relation-aware encoder and feedback training, significantly improving performance across diverse datasets.

Contribution

The paper presents a novel plug-and-play module, Relating-Up, that extends GNNs to effectively model inter-graph relationships using a relation-aware encoder and feedback training strategy.

Findings

Improves GNN expressiveness by capturing inter-graph relationships.

Enhances performance on 16 benchmark datasets.

Provides a versatile, easy-to-integrate module for various GNN architectures.

Abstract

Graph Neural Networks (GNNs) have excelled in learning from graph-structured data, especially in understanding the relationships within a single graph, i.e., intra-graph relationships. Despite their successes, GNNs are limited by neglecting the context of relationships across graphs, i.e., inter-graph relationships. Recognizing the potential to extend this capability, we introduce Relating-Up, a plug-and-play module that enhances GNNs by exploiting inter-graph relationships. This module incorporates a relation-aware encoder and a feedback training strategy. The former enables GNNs to capture relationships across graphs, enriching relation-aware graph representation through collective context. The latter utilizes a feedback loop mechanism for the recursively refinement of these representations, leveraging insights from refining inter-graph dynamics to conduct feedback loop. The synergy between these two innovations results in a robust and versatile module. Relating-Up enhances the expressiveness of GNNs, enabling them to encapsulate a wider spectrum of graph relationships with greater precision. Our evaluations across 16 benchmark datasets demonstrate that integrating Relating-Up into GNN architectures substantially improves performance, positioning Relating-Up as a formidable choice for a broad spectrum of graph representation learning tasks.