# Dimensionwise Separable 2-D Graph Convolution for Unsupervised and Semi-Supervised Learning on Graphs

arXiv: https://arxiv.org/abs/1909.12038 · HTML: https://mlsanity.com/paper/1909.12038/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [A Survey on Graph Representation Learning Methods](https://mlsanity.com/paper/2204.01855/) (2022)
- [A Survey on Spectral Graph Neural Networks](https://mlsanity.com/paper/2302.05631/) (2023)
- [Collaborative Graph Neural Networks for Attributed Network Embedding](https://mlsanity.com/paper/2307.11981/) (2023)
- [A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness](https://mlsanity.com/paper/2406.09675/) (2024)
- [Continual Graph Convolutional Network for Text Classification](https://mlsanity.com/paper/2304.04152/) (2023)
- [Uncertainty-Aware Graph Structure Learning](https://mlsanity.com/paper/2502.12618/) (2025)
- [EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data](https://mlsanity.com/paper/2211.12941/) (2022)
- [Spectral GNN via Two-dimensional (2-D) Graph Convolution](https://mlsanity.com/paper/2404.04559/) (2024)
- [Informative Graph Structure Learning](https://mlsanity.com/paper/2605.16809/) (2026)

## Abstract (arXiv)

Graph convolutional neural networks (GCN) have been the model of choice for graph representation learning, which is mainly due to the effective design of graph convolution that computes the representation of a node by aggregating those of its neighbors. However, existing GCN variants commonly use 1-D graph convolution that solely operates on the object link graph without exploring informative relational information among object attributes. This significantly limits their modeling capability and may lead to inferior performance on noisy and sparse real-world networks. In this paper, we explore 2-D graph convolution to jointly model object links and attribute relations for graph representation learning. Specifically, we propose a computationally efficient dimensionwise separable 2-D graph convolution (DSGC) for filtering node features. Theoretically, we show that DSGC can reduce intra-class variance of node features on both the object dimension and the attribute dimension to learn more effective representations. Empirically, we demonstrate that by modeling attribute relations, DSGC achieves significant performance gain over state-of-the-art methods for node classification and clustering on a variety of real-world networks. The source code for reproducing the experimental results is available at https://github.com/liqimai/DSGC.