# NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification

arXiv: https://arxiv.org/abs/2012.03476 · HTML: https://mlsanity.com/paper/2012.03476/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

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

- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [Graph Neural Networks in Vision-Language Image Understanding: A Survey](https://mlsanity.com/paper/2303.03761/) (2023)
- [AGFormer: Efficient Graph Representation with Anchor-Graph Transformer](https://mlsanity.com/paper/2305.07521/) (2023)
- [Survey of Graph Neural Network for Internet of Things and NextG Networks](https://mlsanity.com/paper/2405.17309/) (2024)
- [Learn from Heterophily: Heterophilous Information-enhanced Graph Neural Network](https://mlsanity.com/paper/2403.17351/) (2024)
- [DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning](https://mlsanity.com/paper/2407.14081/) (2024)
- [Hybrid Gromov-Wasserstein Embedding for Capsule Learning](https://mlsanity.com/paper/2209.00232/) (2022)
- [Mitigating Overfitting in Graph Neural Networks via Feature and Hyperplane Perturbation](https://mlsanity.com/paper/2211.15081/) (2022)
- [Coarse-to-Fine Contrastive Learning on Graphs](https://mlsanity.com/paper/2212.06423/) (2022)

## Abstract (arXiv)

Message passing has evolved as an effective tool for designing Graph Neural Networks (GNNs). However, most existing methods for message passing simply sum or average all the neighboring features to update node representations. They are restricted by two problems, i.e., (i) lack of interpretability to identify node features significant to the prediction of GNNs, and (ii) feature over-mixing that leads to the over-smoothing issue in capturing long-range dependencies and inability to handle graphs under heterophily or low homophily. In this paper, we propose a Node-level Capsule Graph Neural Network (NCGNN) to address these problems with an improved message passing scheme. Specifically, NCGNN represents nodes as groups of node-level capsules, in which each capsule extracts distinctive features of its corresponding node. For each node-level capsule, a novel dynamic routing procedure is developed to adaptively select appropriate capsules for aggregation from a subgraph identified by the designed graph filter. NCGNN aggregates only the advantageous capsules and restrains irrelevant messages to avoid over-mixing features of interacting nodes. Therefore, it can relieve the over-smoothing issue and learn effective node representations over graphs with homophily or heterophily. Furthermore, our proposed message passing scheme is inherently interpretable and exempt from complex post-hoc explanations, as the graph filter and the dynamic routing procedure identify a subset of node features that are most significant to the model prediction from the extracted subgraph. Extensive experiments on synthetic as well as real-world graphs demonstrate that NCGNN can well address the over-smoothing issue and produce better node representations for semisupervised node classification. It outperforms the state of the arts under both homophily and heterophily.