mlsanityData to 14 Oct 2026

Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagation

arXiv 2505.03774 ↗First posted 29 Apr 2025cs.LG cs.SIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are proven effective in extracting complex node and structural information from graph data. While current GNNs perform well in node classification tasks within in-distribution (ID) settings, real-world scenarios often present distribution shifts, leading to the presence of out-of-distribution (OOD) nodes. OOD detection in graphs is a crucial and challenging task. Most existing research focuses on homogeneous graphs, but real-world graphs are often heterogeneous, consisting of diverse node and edge types. This heterogeneity adds complexity and enriches the informational content. To the best of our knowledge, OOD detection in heterogeneous graphs remains an underexplored area. In this context, we propose a novel methodology for OOD detection in heterogeneous graphs (OODHG) that aims to achieve two main objectives: 1) detecting OOD nodes and 2) classifying all ID nodes based on the first task's results. Specifically, we learn representations for each node in the heterogeneous graph, calculate energy values to determine whether nodes are OOD, and then classify ID nodes. To leverage the structural information of heterogeneous graphs, we introduce a meta-path-based energy propagation mechanism and an energy constraint to enhance the distinction between ID and OOD nodes. Extensive experimental findings substantiate the simplicity and effectiveness of OODHG, demonstrating its superiority over baseline models in OOD detection tasks and its accuracy in ID node classification.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 29 Apr 2025.

Builds on

33 of 44 references.

References · 33

  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. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  8. 2018Link Prediction Based on Graph Neural Networkscited by 832
  9. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  10. 2019Heterogeneous Graph Attention Networkcited by 734
  11. 2019Graph Transformer Networkscited by 523
  12. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
21 more
  1. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  2. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  3. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  4. 2017DOC: Deep Open Classification of Text Documentscited by 109
  5. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 96
  6. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  7. 2021Graph Structure Learning with Variational Information Bottleneckcited by 81
  8. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 80
  9. 2022Simple and Efficient Heterogeneous Graph Neural Networkcited by 71
  10. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  11. 2019STAR-GCN: Stacked and Reconstructed Graph Convolutional Networks for Recommender Systemscited by 54
  12. 2022GOOD-D: On Unsupervised Graph Out-Of-Distribution Detectioncited by 47
  13. 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
  14. 2023Open Set Action Recognition via Multi-Label Evidential Learningcited by 26
  15. 2024Supervised Algorithmic Fairness in Distribution Shifts: A Surveycited by 24
  16. 2020Rank-Based Multi-task Learning for Fair Regressioncited by 19
  17. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  18. 2025Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphscited by 9
  19. 2024GDDA: Semantic OOD Detection on Graphs under Covariate Shift via Score-Based Diffusion Modelscited by 5
  20. 2024MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learningcited by 5
  21. 2024Feature-Space Semantic Invariance: Enhanced OOD Detection for Open-Set Domain Generalizationcited by 1

Built on by

Not cited yet.