# CatGCN: Graph Convolutional Networks with Categorical Node Features

arXiv: https://arxiv.org/abs/2009.05303 · HTML: https://mlsanity.com/paper/2009.05303/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2020.

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

- [Deep Partial Multiplex Network Embedding](https://mlsanity.com/paper/2203.02656/) (2022)
- [Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network](https://mlsanity.com/paper/2207.07503/) (2022)
- [Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks](https://mlsanity.com/paper/2312.08651/) (2023)
- [Sequential Learner Modeling Using Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/2607.19253/) (2026)

## Abstract (arXiv)

Recent studies on Graph Convolutional Networks (GCNs) reveal that the initial node representations (i.e., the node representations before the first-time graph convolution) largely affect the final model performance. However, when learning the initial representation for a node, most existing work linearly combines the embeddings of node features, without considering the interactions among the features (or feature embeddings). We argue that when the node features are categorical, e.g., in many real-world applications like user profiling and recommender system, feature interactions usually carry important signals for predictive analytics. Ignoring them will result in suboptimal initial node representation and thus weaken the effectiveness of the follow-up graph convolution. In this paper, we propose a new GCN model named CatGCN, which is tailored for graph learning when the node features are categorical. Specifically, we integrate two ways of explicit interaction modeling into the learning of initial node representation, i.e., local interaction modeling on each pair of node features and global interaction modeling on an artificial feature graph. We then refine the enhanced initial node representations with the neighborhood aggregation-based graph convolution. We train CatGCN in an end-to-end fashion and demonstrate it on semi-supervised node classification. Extensive experiments on three tasks of user profiling (the prediction of user age, city, and purchase level) from Tencent and Alibaba datasets validate the effectiveness of CatGCN, especially the positive effect of performing feature interaction modeling before graph convolution.