# Class-Attentive Diffusion Network for Semi-Supervised Classification

arXiv: https://arxiv.org/abs/2006.10222 · HTML: https://mlsanity.com/paper/2006.10222/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2020.

## Built on by (most cited first, 8 of 8)

- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [A Survey on Graph Structure Learning: Progress and Opportunities](https://mlsanity.com/paper/2103.03036/) (2021)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [Confidence-Based Feature Imputation for Graphs with Partially Known Features](https://mlsanity.com/paper/2305.16618/) (2023)
- [Motif Graph Neural Network](https://mlsanity.com/paper/2112.14900/) (2021)
- [Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting](https://mlsanity.com/paper/2207.05334/) (2022)
- [Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning](https://mlsanity.com/paper/2112.01110/) (2021)
- [Bring the Power of Diffusion Model to Defect Detection](https://mlsanity.com/paper/2408.13845/) (2024)

## Abstract (arXiv)

Recently, graph neural networks for semi-supervised classification have been widely studied. However, existing methods only use the information of limited neighbors and do not deal with the inter-class connections in graphs. In this paper, we propose Adaptive aggregation with Class-Attentive Diffusion (AdaCAD), a new aggregation scheme that adaptively aggregates nodes probably of the same class among K-hop neighbors. To this end, we first propose a novel stochastic process, called Class-Attentive Diffusion (CAD), that strengthens attention to intra-class nodes and attenuates attention to inter-class nodes. In contrast to the existing diffusion methods with a transition matrix determined solely by the graph structure, CAD considers both the node features and the graph structure with the design of our class-attentive transition matrix that utilizes a classifier. Then, we further propose an adaptive update scheme that leverages different reflection ratios of the diffusion result for each node depending on the local class-context. As the main advantage, AdaCAD alleviates the problem of undesired mixing of inter-class features caused by discrepancies between node labels and the graph topology. Built on AdaCAD, we construct a simple model called Class-Attentive Diffusion Network (CAD-Net). Extensive experiments on seven benchmark datasets consistently demonstrate the efficacy of the proposed method and our CAD-Net significantly outperforms the state-of-the-art methods. Code is available at https://github.com/ljin0429/CAD-Net.