Scholarlink

<p>In recent years, Graph Convolutional Networks (GCNs) have attracted considerable attention due to their strong capability in modeling graph-structured data. However, as network depth increases, GCNs often suffer from the over-smoothing phenomenon, where node representations become indistinguishable due to excessive feature aggregation. Existing approaches typically focus on modifying graph topology or propagation mechanisms, but often lack a unified treatment of both the structural causes and representational consequences of over-smoothing. To address this challenge, we propose a novel model named DRS-GCN, which includes two strategies: Dynamic Reorganization (DR) and Smoothness Loss (SL). Specifically, DR leverages Ollivier Ricci Curvature (ORC) together with cosine similarity between node representations to adaptively suppress edges that contribute most to excessive smoothing during message passing. Meanwhile, the SL introduces a regularization loss based on distance between neighbor nodes, which encourages compact node representations for nodes with the same label while promoting separability between those with different labels. We conduct experiments on nine public benchmark datasets of diverse types. The results show that DRS-GCN achieves competitive and often superior performance across multiple datasets, obtaining the best or comparable results on the majority of benchmarks. The code is available at <a href="https://github.com/Cheng-qi/drs-gcn.git">https://github.com/Cheng-qi/drs-gcn.git</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DRS-GCN: Counteracting over-smoothing in graph convolutional networks through dynamic reorganization and smoothness loss

  • 期刊论文

  • 发表日期：

    2026年5月27日

查看全文
  • Qi Cheng,
  • Lang Long,
  • Min Zhang,
  • Chengkui Zhao,
  • Weixing Feng

摘要

In recent years, Graph Convolutional Networks (GCNs) have attracted considerable attention due to their strong capability in modeling graph-structured data. However, as network depth increases, GCNs often suffer from the over-smoothing phenomenon, where node representations become indistinguishable due to excessive feature aggregation. Existing approaches typically focus on modifying graph topology or propagation mechanisms, but often lack a unified treatment of both the structural causes and representational consequences of over-smoothing. To address this challenge, we propose a novel model named DRS-GCN, which includes two strategies: Dynamic Reorganization (DR) and Smoothness Loss (SL). Specifically, DR leverages Ollivier Ricci Curvature (ORC) together with cosine similarity between node representations to adaptively suppress edges that contribute most to excessive smoothing during message passing. Meanwhile, the SL introduces a regularization loss based on distance between neighbor nodes, which encourages compact node representations for nodes with the same label while promoting separability between those with different labels. We conduct experiments on nine public benchmark datasets of diverse types. The results show that DRS-GCN achieves competitive and often superior performance across multiple datasets, obtaining the best or comparable results on the majority of benchmarks. The code is available at https://github.com/Cheng-qi/drs-gcn.git.