mlsanityData to 14 Oct 2026

Addressing Over-Smoothing in Graph Neural Networks via Deep Supervision

arXiv 2202.12508 ↗First posted 25 Feb 2022cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Learning useful node and graph representations with graph neural networks (GNNs) is a challenging task. It is known that deep GNNs suffer from over-smoothing where, as the number of layers increases, node representations become nearly indistinguishable and model performance on the downstream task degrades significantly. To address this problem, we propose deeply-supervised GNNs (DSGNNs), i.e., GNNs enhanced with deep supervision where representations learned at all layers are used for training. We show empirically that DSGNNs are resilient to over-smoothing and can outperform competitive benchmarks on node and graph property prediction problems.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

24 of 40 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  7. 2018Group Normalizationcited by 1,524
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  10. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  12. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
12 more
  1. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  2. 2020Benchmarking Graph Neural Networkscited by 680
  3. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  4. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  5. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  6. 2019Graph U-Netscited by 492
  7. 2019Self-Attention Graph Poolingcited by 421
  8. 2014Deeply-Supervised Netscited by 367
  9. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  10. 2020Towards Deeper Graph Neural Networkscited by 296
  11. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  12. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 2; 2025: 2; 2026: 1.

7 papers.

  1. 2022DropMessage: Unifying Random Dropping for Graph Neural Networkscited by 29
  2. 2022Online Cross-Layer Knowledge Distillation on Graph Neural Networks with Deep Supervisioncited by 1
  3. 2024DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedbackcited by 1
  4. 2024RW-NSGCN: A Robust Approach to Structural Attacks via Negative Samplingcited by 0
  5. 2025Predicting the Performance of Graph Convolutional Networks with Spectral Properties of the Graph Laplaciancited by 0
  6. 2025Layer-to-Layer Knowledge Mixing in Graph Neural Network for Chemical Property Predictioncited by 0
  7. 2026Scale-Aware Learning of Chaotic Dynamics on Unstructured Meshes via Binned Spectral Lossescited by 0