mlsanityData to 7 Oct 2026

SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks

arXiv 2102.05034 ↗First posted 9 Feb 2021cs.LG cs.AIcited by 108

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) work well when the graph structure is provided. However, this structure may not always be available in real-world applications. One solution to this problem is to infer a task-specific latent structure and then apply a GNN to the inferred graph. Unfortunately, the space of possible graph structures grows super-exponentially with the number of nodes and so the task-specific supervision may be insufficient for learning both the structure and the GNN parameters. In this work, we propose the Simultaneous Learning of Adjacency and GNN Parameters with Self-supervision, or SLAPS, a method that provides more supervision for inferring a graph structure through self-supervision. A comprehensive experimental study demonstrates that SLAPS scales to large graphs with hundreds of thousands of nodes and outperforms several models that have been proposed to learn a task-specific graph structure on established benchmarks.

Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). Builds on 53 of its 84 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

53 of 84 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2017Graph Attention Networkscited by 8,854
  7. 2017Inductive Representation Learning on Large Graphscited by 6,284
  8. 2018How Powerful are Graph Neural Networks?cited by 4,355
  9. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  12. 2020Reformer: The Efficient Transformercited by 1,658
38 more
  1. 2020Rethinking Attention with Performerscited by 1,584
  2. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  3. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  4. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  5. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  6. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  7. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  8. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  9. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  10. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 400
  11. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  12. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  13. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  14. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 302
  15. 2018Adversarial Attack on Graph Structured Datacited by 300
  16. 2019Representation Learning for Dynamic Graphs: A Surveycited by 260
  17. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  18. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  19. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  20. 2020Data Augmentation for Graph Neural Networkscited by 200
  21. 2020Graph-Bert: Only Attention is Needed for Learning Graph Representationscited by 176
  22. 2018GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphscited by 164
  23. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  24. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  25. 2020When Does Self-Supervision Help Graph Convolutional Networks?cited by 121
  26. 2020A Survey on The Expressive Power of Graph Neural Networkscited by 111
  27. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  28. 2018Auxiliary Tasks in Multi-task Learningcited by 106
  29. 2019Graph Normalizing Flowscited by 103
  30. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  31. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  32. 2019Graph-Revised Convolutional Networkcited by 58
  33. 2019Learning representations of irregular particle-detector geometry with distance-weighted graph networkscited by 43
  34. 2020Grale: Designing Networks for Graph Learningcited by 28
  35. 2019Graph Neural Networks with Generated Parameters for Relation Extractioncited by 27
  36. 2020Self-supervised Training of Graph Convolutional Networkscited by 24
  37. 2016When is multitask learning effective? Semantic sequence prediction under varying data conditionscited by 21
  38. 2019Deep Iterative and Adaptive Learning for Graph Neural Networkscited by 17

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 22; 2023: 24; 2024: 26; 2025: 15; 2026: 14.

108 papers.

Sort:

By area:

  1. 2021Graph Self-Supervised Learning: A Surveycited by 289
  2. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  3. 2022Towards Unsupervised Deep Graph Structure Learningcited by 112
  4. 2023Graph Foundation Models: Concepts, Opportunities and Challengescited by 101
  5. 2023Everything is Connected: Graph Neural Networkscited by 85
  6. 2023DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusioncited by 85
  7. 2024Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoningcited by 83
  8. 2021A Survey on Graph Structure Learning: Progress and Opportunitiescited by 70
  9. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  10. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  11. 2022Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminatingcited by 57
  12. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
38 more
  1. 2023GSLB: The Graph Structure Learning Benchmarkcited by 49
  2. 2025Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignmentcited by 41
  3. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  4. 2024GraphEdit: Large Language Models for Graph Structure Learningcited by 33
  5. 2023OpenGSL: A Comprehensive Benchmark for Graph Structure Learningcited by 30
  6. 2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
  7. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  8. 2023Learning Strong Graph Neural Networks with Weak Informationcited by 25
  9. 2024A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guidecited by 22
  10. 2021Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactionscited by 20
  11. 2022Self-Supervised Graph Structure Refinement for Graph Neural Networkscited by 20
  12. 2023Causal Deep Learningcited by 20
  13. 2021Self-supervised Contrastive Attributed Graph Clusteringcited by 18
  14. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  15. 2025Edge Prompt Tuning for Graph Neural Networkscited by 18
  16. 2022Structure-Preserving Graph Representation Learningcited by 17
  17. 2021Simultaneous Missing Value Imputation and Structure Learning with Groupscited by 16
  18. 2022Private Graph Extraction via Feature Explanationscited by 16
  19. 2022Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophilycited by 15
  20. 2024DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashingcited by 15
  21. 2024Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptationcited by 15
  22. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  23. 2024DSLR: Diversity Enhancement and Structure Learning for Rehearsal-based Graph Continual Learningcited by 14
  24. 2023RDGSL: Dynamic Graph Representation Learning with Structure Learningcited by 13
  25. 2024Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directionscited by 13
  26. 2024Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learningcited by 12
  27. 2024Robust Graph Structure Learning under Heterophilycited by 11
  28. 2022Restructuring Graph for Higher Homophily via Adaptive Spectral Clusteringcited by 9
  29. 2023Homophily-enhanced Structure Learning for Graph Clusteringcited by 9
  30. 2023UGSL: A Unified Framework for Benchmarking Graph Structure Learningcited by 9
  31. 2023Latent Graph Inference with Limited Supervisioncited by 9
  32. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  33. 2024Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Drivingcited by 9
  34. 2022Self-supervised Graphs for Audio Representation Learning with Limited Labeled Datacited by 8
  35. 2022Self-organization Preserved Graph Structure Learning with Principle of Relevant Informationcited by 8
  36. 2023Learning to Substitute Ingredients in Recipescited by 8
  37. 2023Federated Learning of Models Pre-Trained on Different Features with Consensus Graphscited by 8
  38. 2024Self-Guided Robust Graph Structure Refinementcited by 8

50 most cited of 108 All 108 (JSON)