mlsanityData to 14 Oct 2026

From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited

arXiv 2309.13599 ↗First posted 24 Sep 2023cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Graph-based semi-supervised learning (GSSL) has long been a hot research topic. Traditional methods are generally shallow learners, based on the cluster assumption. Recently, graph convolutional networks (GCNs) have become the predominant techniques for their promising performance. In this paper, we theoretically discuss the relationship between these two types of methods in a unified optimization framework. One of the most intriguing findings is that, unlike traditional ones, typical GCNs may not jointly consider the graph structure and label information at each layer. Motivated by this, we further propose three simple but powerful graph convolution methods. The first is a supervised method OGC which guides the graph convolution process with labels. The others are two unsupervised methods: GGC and its multi-scale version GGCM, both aiming to preserve the graph structure information during the convolution process. Finally, we conduct extensive experiments to show the effectiveness of our methods. Code is available at https://github.com/zhengwang100/ogc_ggcm.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 58 of its 90 references that are in the map. First posted on arXiv 24 Sep 2023.

Builds on

58 of 90 references.

References · 58

  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. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2018How Powerful are Graph Neural Networks?cited by 4,393
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  8. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  9. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
  10. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  11. 2021Convex optimizationcited by 2,515
  12. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
38 more
  1. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  2. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  3. 2019Simplifying Graph Convolutional Networkscited by 1,477
  4. 2016Variational Graph Auto-Encoderscited by 1,382
  5. 2018Deep Graph Infomaxcited by 1,106
  6. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  9. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  10. 2020Simple and Deep Graph Convolutional Networkscited by 860
  11. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  12. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  13. 2015LINE: Large-scale Information Network Embeddingcited by 582
  14. 2022Beyond neural scaling laws: beating power law scaling via data pruningcited by 528
  15. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  16. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  17. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 247
  18. 2020Graph Random Neural Network for Semi-Supervised Learning on Graphscited by 213
  19. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 202
  20. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 186
  21. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 165
  22. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 133
  23. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  24. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  25. 2022Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvaturecited by 98
  26. 2019Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learningcited by 94
  27. 2022How Powerful are K-hop Message Passing Graph Neural Networkscited by 90
  28. 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
  29. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  30. 2023Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothingcited by 67
  31. 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
  32. 2022Understanding convolution on graphs via energiescited by 59
  33. 2018N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classificationcited by 54
  34. 2018VERSE: Versatile Graph Embeddings from Similarity Measurescited by 54
  35. 2020L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networkscited by 48
  36. 2021Node Dependent Local Smoothing for Scalable Graph Learningcited by 45
  37. 2019Improving Graph Attention Networks with Large Margin-based Constraintscited by 34
  38. 2022ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networkscited by 31

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 2.

6 papers.

  1. 2025GraphICL: Unlocking Graph Learning Potential in LLMs through Structured Prompt Designcited by 21
  2. 2024rLLM: Relational Table Learning with LLMscited by 7
  3. 2024Improved Graph-based semi-supervised learning Schemescited by 2
  4. 2025Chem-NMF: Multi-layer α-divergence Non-Negative Matrix Factorization for Cardiorespiratory Disease Clustering, with Improved Convergence Inspired by Chemical Catalysts and Rigorous Asymptotic Analysiscited by 1
  5. 2026InRTL: Effective Intra-Inter Interaction Learning for Relational Tablescited by 0
  6. 2026MetaRTL: Meta-path Attention Enhanced Relational Table Learningcited by 0