# Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations

arXiv: https://arxiv.org/abs/2010.05404 · HTML: https://mlsanity.com/paper/2010.05404/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 4 of 4)

- [Rethinking the Zigzag Flattening for Image Reading](https://mlsanity.com/paper/2202.10240/) (2022)
- [Application of Graph Neural Networks and graph descriptors for graph classification](https://mlsanity.com/paper/2211.03666/) (2022)
- [DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention Detection](https://mlsanity.com/paper/2309.07147/) (2023)
- [Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion](https://mlsanity.com/paper/2603.26729/) (2026)

## Abstract (arXiv)

Graph convolutional networks (GCNs) have been widely used for representation learning on graph data, which can capture structural patterns on a graph via specifically designed convolution and readout operations. In many graph classification applications, GCN-based approaches have outperformed traditional methods. However, most of the existing GCNs are inefficient to preserve local information of graphs -- a limitation that is especially problematic for graph classification. In this work, we propose a locality-preserving dense GCN with graph context-aware node representations. Specifically, our proposed model incorporates a local node feature reconstruction module to preserve initial node features into node representations, which is realized via a simple but effective encoder-decoder mechanism. To capture local structural patterns in neighbourhoods representing different ranges of locality, dense connectivity is introduced to connect each convolutional layer and its corresponding readout with all previous convolutional layers. To enhance node representativeness, the output of each convolutional layer is concatenated with the output of the previous layer's readout to form a global context-aware node representation. In addition, a self-attention module is introduced to aggregate layer-wise representations to form the final representation. Experiments on benchmark datasets demonstrate the superiority of the proposed model over state-of-the-art methods in terms of classification accuracy.