# Revisiting Over-smoothing in Deep GCNs

arXiv: https://arxiv.org/abs/2003.13663 · HTML: https://mlsanity.com/paper/2003.13663/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Mar 2020.

## Built on by (most cited first, 30 of 55)

- [Language is All a Graph Needs](https://mlsanity.com/paper/2308.07134/) (2023)
- [NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs](https://mlsanity.com/paper/2206.04910/) (2022)
- [Pre-training via Denoising for Molecular Property Prediction](https://mlsanity.com/paper/2206.00133/) (2022)
- [On the Connection Between MPNN and Graph Transformer](https://mlsanity.com/paper/2301.11956/) (2023)
- [On Provable Benefits of Depth in Training Graph Convolutional Networks](https://mlsanity.com/paper/2110.15174/) (2021)
- [Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods](https://mlsanity.com/paper/2111.04840/) (2021)
- [Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs](https://mlsanity.com/paper/2311.01015/) (2023)
- [Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond](https://mlsanity.com/paper/2106.07971/) (2021)
- [Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study](https://mlsanity.com/paper/2108.10521/) (2021)
- [Transformers from an Optimization Perspective](https://mlsanity.com/paper/2205.13891/) (2022)
- [Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs](https://mlsanity.com/paper/2306.05628/) (2023)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks](https://mlsanity.com/paper/2107.10234/) (2021)
- [Evaluating Deep Graph Neural Networks](https://mlsanity.com/paper/2108.00955/) (2021)
- [GATE: Graph CCA for Temporal SElf-supervised Learning for Label-efficient fMRI Analysis](https://mlsanity.com/paper/2203.09034/) (2022)
- [Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning](https://mlsanity.com/paper/2505.15547/) (2025)
- [Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization](https://mlsanity.com/paper/2305.19903/) (2023)
- [RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph](https://mlsanity.com/paper/2202.06129/) (2022)
- [From Local to Global: Spectral-Inspired Graph Neural Networks](https://mlsanity.com/paper/2209.12054/) (2022)
- [Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again](https://mlsanity.com/paper/2210.08122/) (2022)
- [SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks](https://mlsanity.com/paper/2112.11628/) (2021)
- [Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation](https://mlsanity.com/paper/2407.10528/) (2024)
- [GRANOLA: Adaptive Normalization for Graph Neural Networks](https://mlsanity.com/paper/2404.13344/) (2024)
- [SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks](https://mlsanity.com/paper/2102.10338/) (2021)
- [SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators](https://mlsanity.com/paper/2301.10388/) (2023)
- [Tokenized Graph Transformer with Neighborhood Augmentation for Node Classification in Large Graphs](https://mlsanity.com/paper/2305.12677/) (2023)
- [Differential-Integral Neural Operator for Long-Term Turbulence Forecasting](https://mlsanity.com/paper/2509.21196/) (2025)
- [Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective](https://mlsanity.com/paper/2211.06605/) (2022)
- [Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations](https://mlsanity.com/paper/2306.11668/) (2023)
- [DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning](https://mlsanity.com/paper/2407.18523/) (2024)

## Abstract (arXiv)

Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs). In this paper, we propose a new view that deep GCNs can actually learn to anti-oversmooth during training. This work interprets a standard GCN architecture as layerwise integration of a Multi-layer Perceptron (MLP) and graph regularization. We analyze and conclude that before training, the final representation of a deep GCN does over-smooth, however, it learns anti-oversmoothing during training. Based on the conclusion, the paper further designs a cheap but effective trick to improve GCN training. We verify our conclusions and evaluate the trick on three citation networks and further provide insights on neighborhood aggregation in GCNs.