mlsanityData to 14 Oct 2026

SGOOD: Substructure-enhanced Graph-Level Out-of-Distribution Detection

arXiv 2310.10237 ↗First posted 16 Oct 2023cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Graph-level representation learning is important in a wide range of applications. Existing graph-level models are generally built on i.i.d. assumption for both training and testing graphs. However, in an open world, models can encounter out-of-distribution (OOD) testing graphs that are from different distributions unknown during training. A trustworthy model should be able to detect OOD graphs to avoid unreliable predictions, while producing accurate in-distribution (ID) predictions. To achieve this, we present SGOOD, a novel graph-level OOD detection framework. We find that substructure differences commonly exist between ID and OOD graphs, and design SGOOD with a series of techniques to encode task-agnostic substructures for effective OOD detection. Specifically, we build a super graph of substructures for every graph, and develop a two-level graph encoding pipeline that works on both original graphs and super graphs to obtain substructure-enhanced graph representations. We then devise substructure-preserving graph augmentation techniques to further capture more substructure semantics of ID graphs. Extensive experiments against 11 competitors on numerous graph datasets demonstrate the superiority of SGOOD, often surpassing existing methods by a significant margin. The code is available at https://github.com/TommyDzh/SGOOD.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 40 of its 59 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

40 of 59 references.

References · 40

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  9. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  10. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  12. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
28 more
  1. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  3. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  4. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  5. 2019Graph U-Netscited by 492
  6. 2019Self-Attention Graph Poolingcited by 421
  7. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  8. 2020Can Graph Neural Networks Count Substructures?cited by 236
  9. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  10. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  11. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 155
  12. 2021Nested Graph Neural Networkscited by 137
  13. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  14. 2022Understanding and Extending Subgraph GNNs by Rethinking Their Symmetriescited by 112
  15. 2021User Preference-aware Fake News Detectioncited by 79
  16. 2021OOD-GNN: Out-of-Distribution Generalized Graph Neural Networkcited by 78
  17. 2019Deep Set Prediction Networkscited by 71
  18. 2019Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Networkcited by 68
  19. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  20. 2021Deep Graph-level Anomaly Detection by Glocal Knowledge Distillationcited by 67
  21. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  22. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  23. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  24. 2022Graph-based Molecular Representation Learningcited by 51
  25. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  26. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  27. 2022Deep Generative Model for Periodic Graphscited by 20
  28. 2019Effective Stabilized Self-Training on Few-Labeled Graph Datacited by 4

Built on by

Cited by year (2026 to 14 Oct)

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

7 papers.

  1. 2024A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challengescited by 54
  2. 2024A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptationcited by 17
  3. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  4. 2024GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attentioncited by 1
  5. 2025Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detectioncited by 1
  6. 2025G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognitioncited by 0
  7. 2026Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Modelscited by 0