Layer Embedding Deep Fusion Graph Neural Network

TL;DR

LEDF-GNN is a novel graph neural network framework that enhances deep message passing by fusing multi-layer embeddings and employing dual topologies, improving performance on diverse graph types.

Contribution

The paper introduces LEDF-GNN, a new GNN model with a layer embedding fusion operator and dual topology strategy to address deep propagation issues and heterophily.

Findings

LEDF-GNN outperforms state-of-the-art methods on citation and image benchmarks.

The model effectively handles both homophilic and heterophilic graphs.

Extensive experiments validate its robustness and generalization.

Abstract

Graph Neural Networks (GNNs) have demonstrated impressive performance in learning representations from graph-structured data. However, their message-passing mechanism inherently relies on the assumption of label consistency among connected nodes, limiting their applicability to low-homophily settings. Moreover, since message passing operates as a hierarchical diffusion process, GNNs face challenges in capturing long-range dependencies. As network depth increases, the structural noise along heterophilic edges tends to be amplified, resulting in over-smoothing. This issue becomes especially prominent in highly heterophilic graphs, where the propagation of inconsistent semantics across the topology continually exacerbates misaggregation. To address this issue, we propose a novel framework named Layer Embedding Deep Fusion Graph Neural Network (LEDF-GNN). Specifically, we design a Layer Embedding Deep Fusion (LEDF) operator that nonlinearly fuses multi-layer embeddings to capture inter-layer dependencies and effectively alleviate deep propagation degradation. Meanwhile, to mitigate structural heterophily, LEDF-GNN employs a Dual-Topology Parallel Strategy (DTPS) that simultaneously leverages the original and reconstructed topologies, allowing for adaptive structure-semantics co-optimization under diverse homophily conditions. Extensive semi-supervised classification experiments on the citation and image benchmarks demonstrate that, under both homophilic and heterophilic settings, LEDF-GNN consistently outperforms state-of-the-art baselines, validating its effectiveness and generalization capability across diverse graph types.