# AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing

arXiv: https://arxiv.org/abs/2304.07014 · HTML: https://mlsanity.com/paper/2304.07014/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 67 references that are in the map.
- First posted on arXiv 14 Apr 2023.

## Builds on (most cited first, 26 of 26)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Simple and Deep Graph Convolutional Networks](https://mlsanity.com/paper/2007.02133/) (2020)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations](https://mlsanity.com/paper/2108.01938/) (2021)
- [Adaptive Graph Encoder for Attributed Graph Embedding](https://mlsanity.com/paper/2007.01594/) (2020)
- [Graph Contrastive Clustering](https://mlsanity.com/paper/2104.01429/) (2021)
- [Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks](https://mlsanity.com/paper/2003.08414/) (2020)
- [AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models](https://mlsanity.com/paper/1908.05081/) (2019)
- [Understanding Structural Vulnerability in Graph Convolutional Networks](https://mlsanity.com/paper/2108.06280/) (2021)
- [Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters](https://mlsanity.com/paper/2006.15516/) (2020)
- [SOGNet: Scene Overlap Graph Network for Panoptic Segmentation](https://mlsanity.com/paper/1911.07527/) (2019)
- [Power up! Robust Graph Convolutional Network via Graph Powering](https://mlsanity.com/paper/1905.10029/) (2019)
- [Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification](https://mlsanity.com/paper/1904.04238/) (2019)
- [Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning](https://mlsanity.com/paper/2211.09155/) (2022)
- [Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network](https://mlsanity.com/paper/2006.06478/) (2020)
- [AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction](https://mlsanity.com/paper/2106.08732/) (2021)
- [General Partial Label Learning via Dual Bipartite Graph Autoencoder](https://mlsanity.com/paper/2001.01290/) (2020)
- [G3SR: Global Graph Guided Session-based Recommendation](https://mlsanity.com/paper/2203.06467/) (2022)

## Built on by (most cited first, 7 of 7)

- [Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach](https://mlsanity.com/paper/2506.13083/) (2025)
- [A Unified Framework for Combinatorial Optimization Based on Graph Neural Networks](https://mlsanity.com/paper/2406.13125/) (2024)
- [Hypergraph Neural Network with State Space Models for Node Classification](https://mlsanity.com/paper/2508.06587/) (2025)
- [Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering](https://mlsanity.com/paper/2510.02731/) (2025)
- [Scalable Property Valuation Models via Graph-based Deep Learning](https://mlsanity.com/paper/2405.06553/) (2024)
- [Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors](https://mlsanity.com/paper/2504.13426/) (2025)
- [ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning](https://mlsanity.com/paper/2512.14619/) (2025)

## Abstract (arXiv)

Graph Convolutional Network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of the existing GCN-based models suffer from the notorious over-smoothing issue, owing to which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should be beneficial to propagating information across remote neighbors. Recent works have devoted effort to addressing over-smoothing problems, including establishing residual connection structure or fusing predictions from multi-layer models. Because of the indistinguishable embeddings from deep layers, it is reasonable to generate more reliable predictions before conducting the combination of outputs from various layers. In light of this, we propose an Alternating Graph-regularized Neural Network (AGNN) composed of Graph Convolutional Layer (GCL) and Graph Embedding Layer (GEL). GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem by periodic projection from the low-order feature space onto the high-order space. With more distinguishable features of distinct layers, an improved Adaboost strategy is utilized to aggregate outputs from each layer, which explores integrated embeddings of multi-hop neighbors. The proposed model is evaluated via a large number of experiments including performance comparison with some multi-layer or multi-order graph neural networks, which reveals the superior performance improvement of AGNN compared with state-of-the-art models.