# Reducing Over-smoothing in Graph Neural Networks Using Relational Embeddings

arXiv: https://arxiv.org/abs/2301.02924 · HTML: https://mlsanity.com/paper/2301.02924/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 7 Jan 2023.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [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)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [DropEdge: Towards Deep Graph Convolutional Networks on Node Classification](https://mlsanity.com/paper/1907.10903/) (2019)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](https://mlsanity.com/paper/1705.02364/) (2017)
- [PairNorm: Tackling Oversmoothing in GNNs](https://mlsanity.com/paper/1909.12223/) (2019)
- [A Note on Over-Smoothing for Graph Neural Networks](https://mlsanity.com/paper/2006.13318/) (2020)
- [Towards Deeper Graph Neural Networks with Differentiable Group Normalization](https://mlsanity.com/paper/2006.06972/) (2020)
- [Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks](https://mlsanity.com/paper/1906.02174/) (2019)

## Built on by (most cited first, 2 of 2)

- [DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text](https://mlsanity.com/paper/2310.12557/) (2023)
- [Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions](https://mlsanity.com/paper/2604.24293/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved a lot of success with graph-structured data. However, it is observed that the performance of GNNs does not improve (or even worsen) as the number of layers increases. This effect has known as over-smoothing, which means that the representations of the graph nodes of different classes would become indistinguishable when stacking multiple layers. In this work, we propose a new simple, and efficient method to alleviate the effect of the over-smoothing problem in GNNs by explicitly using relations between node embeddings. Experiments on real-world datasets demonstrate that utilizing node embedding relations makes GNN models such as Graph Attention Network more robust to over-smoothing and achieves better performance with deeper GNNs. Our method can be used in combination with other methods to give the best performance. GNN applications are endless and depend on the user's objective and the type of data that they possess. Solving over-smoothing issues can potentially improve the performance of models on all these tasks.