Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BuffGraph: Enhancing Class-Imbalanced Node Classification via Buffer Nodes (2402.13114v1)

Published 20 Feb 2024 in cs.LG and cs.AI

Abstract: Class imbalance in graph-structured data, where minor classes are significantly underrepresented, poses a critical challenge for Graph Neural Networks (GNNs). To address this challenge, existing studies generally generate new minority nodes and edges connecting new nodes to the original graph to make classes balanced. However, they do not solve the problem that majority classes still propagate information to minority nodes by edges in the original graph which introduces bias towards majority classes. To address this, we introduce BuffGraph, which inserts buffer nodes into the graph, modulating the impact of majority classes to improve minor class representation. Our extensive experiments across diverse real-world datasets empirically demonstrate that BuffGraph outperforms existing baseline methods in class-imbalanced node classification in both natural settings and imbalanced settings. Code is available at https://anonymous.4open.science/r/BuffGraph-730A.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (31)
  1. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In international conference on machine learning. PMLR, 21–29.
  2. Half-Hop: A graph upsampling approach for slowing down message passing. In International Conference on Machine Learning. PMLR, 1341–1360.
  3. A Graph Neural Network Approach for Identification of Influencers and Micro-Influencers in a Social Network:* Classifying influencers from non-influencers using GNN and GCN. In 2023 International Conference on Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS). IEEE, 66–71.
  4. A comprehensive survey of graph embedding: Problems, techniques, and applications. IEEE transactions on knowledge and data engineering 30, 9 (2018), 1616–1637.
  5. Deep neural networks for learning graph representations. In Proceedings of the AAAI conference on artificial intelligence, Vol. 30.
  6. Inductive representation learning on large graphs. Advances in neural information processing systems 30 (2017).
  7. Haibo He and Edwardo A Garcia. 2009. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering 21, 9 (2009), 1263–1284.
  8. Disentangling label distribution for long-tailed visual recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 6626–6636.
  9. Nicolas Keriven. 2022. Not too little, not too much: a theoretical analysis of graph (over) smoothing. Advances in Neural Information Processing Systems 35 (2022), 2268–2281.
  10. Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
  11. GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification. arXiv preprint arXiv:2306.09612 (2023).
  12. Ethereum transaction tracking: Inferring evolution of transaction networks via link prediction. Physica A: Statistical Mechanics and its Applications 600 (2022), 127504.
  13. Péter Mernyei and Cătălina Cangea. 2020. Wiki-cs: A wikipedia-based benchmark for graph neural networks. arXiv preprint arXiv:2007.02901 (2020).
  14. Graphens: Neighbor-aware ego network synthesis for class-imbalanced node classification. In The Tenth International Conference on Learning Representations, ICLR 2022. International Conference on Learning Representations (ICLR).
  15. Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv:2002.05287 (2020).
  16. Object-part attention model for fine-grained image classification. IEEE Transactions on Image Processing 27, 3 (2017), 1487–1500.
  17. Imgagn: Imbalanced network embedding via generative adversarial graph networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 1390–1398.
  18. Balanced meta-softmax for long-tailed visual recognition. Advances in neural information processing systems 33 (2020), 4175–4186.
  19. Collective classification in network data. AI magazine 29, 3 (2008), 93–93.
  20. Chartalist: Labeled Graph Datasets for UTXO and Account-based Blockchains. Advances in Neural Information Processing Systems 35 (2022), 34926–34939.
  21. Pitfalls of graph neural network evaluation. arXiv preprint arXiv:1811.05868 (2018).
  22. Multi-class imbalanced graph convolutional network learning. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20).
  23. TAM: topology-aware margin loss for class-imbalanced node classification. In International Conference on Machine Learning. PMLR, 20369–20383.
  24. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
  25. ETGraph: A Pioneering Dataset Bridging Ethereum and Twitter. arXiv preprint arXiv:2310.01015 (2023).
  26. Two sides of the same coin: Heterophily and oversmoothing in graph convolutional neural networks. In 2022 IEEE International Conference on Data Mining (ICDM). IEEE, 1287–1292.
  27. Graphsmote: Imbalanced node classification on graphs with graph neural networks. In Proceedings of the 14th ACM international conference on web search and data mining. 833–841.
  28. Graph neural networks for graphs with heterophily: A survey. arXiv preprint arXiv:2202.07082 (2022).
  29. Mengting Zhou and Zhiguo Gong. 2023. GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification. arXiv preprint arXiv:2302.12814 (2023).
  30. Graph neural networks with heterophily. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 11168–11176.
  31. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in neural information processing systems 33 (2020), 7793–7804.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Qian Wang (453 papers)
  2. Zemin Liu (28 papers)
  3. Zhen Zhang (384 papers)
  4. Bingsheng He (105 papers)

Summary

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

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