Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

HGOE: Hybrid External and Internal Graph Outlier Exposure for Graph Out-of-Distribution Detection (2407.21742v1)

Published 31 Jul 2024 in cs.LG and cs.AI

Abstract: With the progressive advancements in deep graph learning, out-of-distribution (OOD) detection for graph data has emerged as a critical challenge. While the efficacy of auxiliary datasets in enhancing OOD detection has been extensively studied for image and text data, such approaches have not yet been explored for graph data. Unlike Euclidean data, graph data exhibits greater diversity but lower robustness to perturbations, complicating the integration of outliers. To tackle these challenges, we propose the introduction of \textbf{H}ybrid External and Internal \textbf{G}raph \textbf{O}utlier \textbf{E}xposure (HGOE) to improve graph OOD detection performance. Our framework involves using realistic external graph data from various domains and synthesizing internal outliers within ID subgroups to address the poor robustness and presence of OOD samples within the ID class. Furthermore, we develop a boundary-aware OE loss that adaptively assigns weights to outliers, maximizing the use of high-quality OOD samples while minimizing the impact of low-quality ones. Our proposed HGOE framework is model-agnostic and designed to enhance the effectiveness of existing graph OOD detection models. Experimental results demonstrate that our HGOE framework can significantly improve the performance of existing OOD detection models across all 8 real datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Stochastic blockmodel approximation of a graphon: Theory and consistent estimation. Advances in Neural Information Processing Systems 26 (2013).
  2. LOF: identifying density-based local outliers. In Proceedings of the 2000 ACM SIGMOD international conference on Management of data. 93–104.
  3. Dual quaternion knowledge graph embeddings. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 6894–6902.
  4. Otkge: Multi-modal knowledge graph embeddings via optimal transport. Advances in Neural Information Processing Systems 35 (2022), 39090–39102.
  5. Sourav Chatterjee. 2015. Matrix estimation by universal singular value thresholding. (2015).
  6. Beware of Overcorrection: Scene-induced Commonsense Graph for Scene Graph Generation. In Proceedings of the 31st ACM International Conference on Multimedia. 2888–2897.
  7. A review: Knowledge reasoning over knowledge graph. Expert Systems with Applications 141 (2020), 112948.
  8. Eliciting structural and semantic global knowledge in unsupervised graph contrastive learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37. 7378–7386.
  9. Data augmentation for deep graph learning: A survey. ACM SIGKDD Explorations Newsletter 24, 2 (2022), 61–77.
  10. Vos: Learning what you don’t know by virtual outlier synthesis. arXiv preprint arXiv:2202.01197 (2022).
  11. One-shot scene graph generation. In Proceedings of the 28th ACM International Conference on Multimedia. 3090–3098.
  12. A Data-centric Framework to Endow Graph Neural Networks with Out-Of-Distribution Detection Ability. (2023).
  13. Graph neural network: Current state of Art, challenges and applications. Materials Today: Proceedings 46 (2021), 10927–10932.
  14. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  15. G-mixup: Graph data augmentation for graph classification. In International Conference on Machine Learning. PMLR, 8230–8248.
  16. ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38. 8481–8489.
  17. Dan Hendrycks and Kevin Gimpel. 2016. A baseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016).
  18. Deep anomaly detection with outlier exposure. arXiv preprint arXiv:1812.04606 (2018).
  19. Collaborative Fraud Detection: How Collaboration Impacts Fraud Detection. In Proceedings of the 31st ACM International Conference on Multimedia. 8891–8899.
  20. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems 33 (2020), 22118–22133.
  21. Graph-mlp: Node classification without message passing in graph. arXiv preprint arXiv:2106.04051 (2021).
  22. What to select: Pursuing consistent motion segmentation from multiple geometric models. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 1708–1716.
  23. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
  24. A simple unified framework for detecting out-of-distribution samples and adversarial attacks. Advances in neural information processing systems 31 (2018).
  25. Graphde: A generative framework for debiased learning and out-of-distribution detection on graphs. Advances in Neural Information Processing Systems 35 (2022), 30277–30290.
  26. Quaternion-based knowledge graph network for recommendation. In Proceedings of the 28th ACM international conference on multimedia. 880–888.
  27. Enhancing the reliability of out-of-distribution image detection in neural networks. arXiv preprint arXiv:1706.02690 (2017).
  28. AUC: a statistically consistent and more discriminating measure than accuracy. In Ijcai, Vol. 3. 519–524.
  29. Graph Mixup with Soft Alignments. arXiv preprint arXiv:2306.06788 (2023).
  30. Isolation forest. In 2008 eighth ieee international conference on data mining. IEEE, 413–422.
  31. Good-d: On unsupervised graph out-of-distribution detection. In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining. 339–347.
  32. Pre-training graph transformer with multimodal side information for recommendation. In Proceedings of the 29th ACM International Conference on Multimedia. 2853–2861.
  33. László Lovász. 2012. Large networks and graph limits. Vol. 60. American Mathematical Soc.
  34. Graph convolutional multi-modal hashing for flexible multimedia retrieval. In Proceedings of the 29th ACM International Conference on Multimedia. 1414–1422.
  35. Deep graph-level anomaly detection by glocal knowledge distillation. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 704–714.
  36. Yixuan Ma and Kun Zhan. 2023. Self-Contrastive Graph Diffusion Network. In Proceedings of the 31st ACM International Conference on Multimedia. 3857–3865.
  37. Larry M Manevitz and Malik Yousef. 2001. One-class SVMs for document classification. Journal of machine Learning research 2, Dec (2001), 139–154.
  38. Tudataset: A collection of benchmark datasets for learning with graphs. arXiv preprint arXiv:2007.08663 (2020).
  39. PSNEA: Pseudo-siamese network for entity alignment between multi-modal knowledge graphs. In Proceedings of the 31st ACM International Conference on Multimedia. 3489–3497.
  40. Hoang Nt and Takanori Maehara. 2019. Revisiting graph neural networks: All we have is low-pass filters. arXiv preprint arXiv:1905.09550 (2019).
  41. Popularity-Aware Graph Social Recommendation for Fully Non-Interaction Users. In Proceedings of the 4th ACM International Conference on Multimedia in Asia. 1–5.
  42. Multimodal graph-based event detection and summarization in social media streams. In Proceedings of the 23rd ACM international conference on Multimedia. 189–192.
  43. Ssd: A unified framework for self-supervised outlier detection. arXiv preprint arXiv:2103.12051 (2021).
  44. Weisfeiler-lehman graph kernels. Journal of Machine Learning Research 12, 9 (2011).
  45. Infograph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization. arXiv preprint arXiv:1908.01000 (2019).
  46. React: Out-of-distribution detection with rectified activations. Advances in Neural Information Processing Systems 34 (2021), 144–157.
  47. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
  48. Graph attention networks. stat 1050, 20 (2017), 10–48550.
  49. Lilapati Waikhom and Ripon Patgiri. 2021. Graph neural networks: Methods, applications, and opportunities. arXiv preprint arXiv:2108.10733 (2021).
  50. Watermarking for Out-of-distribution Detection. Advances in Neural Information Processing Systems 35 (2022), 15545–15557.
  51. Xiyuan Wang and Muhan Zhang. 2022. How powerful are spectral graph neural networks. In International Conference on Machine Learning. PMLR, 23341–23362.
  52. Openauc: Towards auc-oriented open-set recognition. Advances in Neural Information Processing Systems 35 (2022), 25033–25045.
  53. Graph-refined convolutional network for multimedia recommendation with implicit feedback. In Proceedings of the 28th ACM international conference on multimedia. 3541–3549.
  54. MMGCN: Multi-modal graph convolution network for personalized recommendation of micro-video. In Proceedings of the 27th ACM international conference on multimedia. 1437–1445.
  55. Asiri Wijesinghe and Qing Wang. 2022. A new perspective on” how graph neural networks go beyond weisfeiler-lehman?”. In International Conference on Learning Representations.
  56. Learning graphons via structured gromov-wasserstein barycenters. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 10505–10513.
  57. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018).
  58. Generalized out-of-distribution detection: A survey. arXiv preprint arXiv:2110.11334 (2021).
  59. Learning with multiclass AUC: Theory and algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 11 (2021), 7747–7763.
  60. Dynamic gcn: Context-enriched topology learning for skeleton-based action recognition. In Proceedings of the 28th ACM international conference on multimedia. 55–63.
  61. Heterogeneous Graph-based Video Search Reranking using Web Knowledge via Social Media Network. In Proceedings of the 23rd ACM international conference on Multimedia. 871–874.
  62. Graph Contrastive Learning with Augmentations. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 5812–5823. https://proceedings.neurips.cc/paper/2020/file/3fe230348e9a12c13120749e3f9fa4cd-Paper.pdf
  63. Graph based Spatial-temporal Fusion for Multi-modal Person Re-identification. In Proceedings of the 31st ACM International Conference on Multimedia. 3736–3744.
  64. Lingxiao Zhao and Leman Akoglu. 2023. On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights. Big Data 11, 3 (2023), 151–180.
  65. Pattern recognition-based chillers fault detection method using Support Vector Data Description (SVDD). Applied Energy 112 (2013), 1041–1048.
  66. Multimodal relation extraction with efficient graph alignment. In Proceedings of the 29th ACM international conference on multimedia. 5298–5306.
  67. Graph neural networks: A review of methods and applications. AI open 1 (2020), 57–81.
  68. Interpreting and unifying graph neural networks with an optimization framework. In Proceedings of the Web Conference 2021. 1215–1226.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets