Layer Embedding Deep Fusion Graph Neural Network

2026-04-25

AI Summary

Traditional graph neural networks (GNNs) suffer from limited performance on low-homophily graphs due to their reliance on label consistency, and deep propagation often leads to over-smoothing and loss of long-range dependencies. To address these challenges, this work proposes the LEDF-GNN framework, which introduces a Layer-Embedded Deep Fusion (LEDF) operator to nonlinearly integrate multi-layer representations, thereby mitigating representation degradation in deep architectures. Additionally, a Dual-Topology Parallel Strategy (DTPS) is designed to jointly optimize both the original and a reconstructed graph topology, enabling adaptive collaborative learning across both high- and low-homophily settings. Extensive experiments on citation and image benchmarks demonstrate that LEDF-GNN significantly outperforms state-of-the-art models in semi-supervised node classification tasks, exhibiting strong generalization capability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• heterophily
• over-smoothing
• long-range dependencies
• graph neural networks
• message passing

Innovation

• Layer Embedding Deep Fusion
• Dual-Topology Parallel Strategy
• Heterophilic Graphs
• Over-smoothing Mitigation
• Graph Neural Networks