mlsanityData to 14 Oct 2026

UGSL: A Unified Framework for Benchmarking Graph Structure Learning

arXiv 2308.10737 ↗First posted 21 Aug 2023cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) demonstrate outstanding performance in a broad range of applications. While the majority of GNN applications assume that a graph structure is given, some recent methods substantially expanded the applicability of GNNs by showing that they may be effective even when no graph structure is explicitly provided. The GNN parameters and a graph structure are jointly learned. Previous studies adopt different experimentation setups, making it difficult to compare their merits. In this paper, we propose a benchmarking strategy for graph structure learning using a unified framework. Our framework, called Unified Graph Structure Learning (UGSL), reformulates existing models into a single model. We implement a wide range of existing models in our framework and conduct extensive analyses of the effectiveness of different components in the framework. Our results provide a clear and concise understanding of the different methods in this area as well as their strengths and weaknesses. The benchmark code is available at https://github.com/google-research/google-research/tree/master/ugsl.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 21 Aug 2023.

Builds on

36 of 45 references.

References · 36

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  8. 2020Rethinking Attention with Performerscited by 1,601
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  10. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
  11. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  12. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 713
24 more
  1. 2015Image-based Recommendations on Styles and Substitutescited by 706
  2. 2020A Generalization of Transformer Networks to Graphscited by 661
  3. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  4. 2019Graph Transformer Networkscited by 523
  5. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 443
  6. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  7. 2019Learning Discrete Structures for Graph Neural Networkscited by 231
  8. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 214
  9. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  10. 2020Graph-Bert: Only Attention is Needed for Learning Graph Representationscited by 177
  11. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  12. 2023Exphormer: Sparse Transformers for Graphscited by 170
  13. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  14. 2022Towards Unsupervised Deep Graph Structure Learningcited by 114
  15. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 110
  16. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  17. 2019Graph-Revised Convolutional Networkcited by 59
  18. 2022GraphWorld: Fake Graphs Bring Real Insights for GNNscited by 56
  19. 2018End-to-End Retrieval in Continuous Spacecited by 46
  20. 2017Self-Taught Convolutional Neural Networks for Short Text Clusteringcited by 34
  21. 2020Grale: Designing Networks for Graph Learningcited by 28
  22. 2022TF-GNN: Graph Neural Networks in TensorFlowcited by 21
  23. 2019Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networkscited by 2
  24. 2022Stars: Tera-Scale Graph Building for Clustering and Graph Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 2; 2026: 1.

9 papers.

  1. 2024Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoningcited by 88
  2. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  3. 2023Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreachingcited by 24
  4. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  5. 2023Latent Graph Inference with Limited Supervisioncited by 9
  6. 2025Principled Data Augmentation for Learning to Solve Quadratic Programming Problemscited by 2
  7. 2024Motif-driven Subgraph Structure Learning for Graph Classificationcited by 1
  8. 2025OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Taskscited by 0
  9. 2026GraIP: A Benchmarking Framework For Neural Graph Inverse Problemscited by 0