Running summarizing tools on a new article

Check the paper below, then start its synthesis.


LDA-GCN: Localized Differential Attention for Graph Convolutional Network

Guicai Yang (Civil Aviation University of China), Min Lu (Civil Aviation University of China), Hua Ji (Civil Aviation University of China), Guoyu Wang (Beijing Jiaotong University), Jiwen Xie (Civil Aviation University of China), Xiaodong Yan

International Conference on Computer Supported Cooperative Work in Design (CSCWD)
License: not stated (all rights reserved)

Abstract: Graph Convolutional Networks (GCNs) have demonstrated significant efficacy in graph representation learning. Existing approaches often rely on stacking multiple GCN layers to incorporate high-order neighborhood information. How-ever, deeper GCN architectures tend to learn similar node representations by more focusing on the global topology of the graph, thereby diminishing the influence of local structures and leading to over-smoothing. To address this, we propose a Localized Differential Attention Graph Convolutional Network (LDA -GCN), designed to enhance the preservation of local structural information. LDA-GCN introduces a localized differential attention mechanism that diversifies node representations and includes a drop aggregation module to strengthen the robustness of this differential attention. Extensive experiments conducted on several benchmark datasets confirm that LDA-GCN achieves superior performance compared to state-of-the-art methods.

Published on 05 May. 2025