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

Discovering Invariant Neighborhood Patterns for Heterophilic Graphs (2403.10572v1)

Published 15 Mar 2024 in cs.LG and cs.SI

Abstract: This paper studies the problem of distribution shifts on non-homophilous graphs Mosting existing graph neural network methods rely on the homophilous assumption that nodes from the same class are more likely to be linked. However, such assumptions of homophily do not always hold in real-world graphs, which leads to more complex distribution shifts unaccounted for in previous methods. The distribution shifts of neighborhood patterns are much more diverse on non-homophilous graphs. We propose a novel Invariant Neighborhood Pattern Learning (INPL) to alleviate the distribution shifts problem on non-homophilous graphs. Specifically, we propose the Adaptive Neighborhood Propagation (ANP) module to capture the adaptive neighborhood information, which could alleviate the neighborhood pattern distribution shifts problem on non-homophilous graphs. We propose Invariant Non-Homophilous Graph Learning (INHGL) module to constrain the ANP and learn invariant graph representation on non-homophilous graphs. Extensive experimental results on real-world non-homophilous graphs show that INPL could achieve state-of-the-art performance for learning on large non-homophilous graphs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. Mixhop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In ICML, 2019.
  2. Invariant risk minimization. arXiv preprint arXiv:1907.02893, 2019.
  3. Simple and deep graph convolutional networks. In International Conference on Machine Learning, pages 1725–1735. PMLR, 2020.
  4. Ba-gnn: On learning bias-aware graph neural network. In 2022 IEEE 38th International Conference on Data Engineering (ICDE), pages 3012–3024. IEEE, 2022.
  5. Adaptive universal generalized pagerank graph neural network. arXiv preprint arXiv:2006.07988, 2020.
  6. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997, 2018.
  7. Deep learning. MIT press, 2016.
  8. Identity matters in deep learning. arXiv preprint arXiv:1611.04231, 2016.
  9. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  10. Categorical reparameterization with gumbel-softmax. arXiv, 2016.
  11. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  12. Out-of-distribution generalization with maximal invariant predictor. CoRR, abs/2008.01883, 2020. URL https://arxiv.org/abs/2008.01883.
  13. Large scale learning on non-homophilous graphs: New benchmarks and strong simple methods. Advances in Neural Information Processing Systems, 34:20887–20902, 2021.
  14. The concrete distribution: A continuous relaxation of discrete random variables. arXiv, 2016.
  15. Shashank Pandit. A fast and scalable system for fraud detection in online auction networks. World Wide Web, 2007, 2007.
  16. Geom-gcn: Geometric graph convolutional networks. arXiv preprint arXiv:2002.05287, 2020.
  17. Causal inference using invariant prediction: identification and confidence intervals. arxiv. Methodology, 2015.
  18. Imgagn: Imbalanced network embedding via generative adversarial graph networks. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 1390–1398, 2021.
  19. Investigating and mitigating degree-related biases in graph convoltuional networks. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 1435–1444, 2020.
  20. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  21. Community preserving network embedding. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017.
  22. Handling distribution shifts on graphs: An invariance perspective. arXiv preprint arXiv:2202.02466, 2022.
  23. Representation learning on graphs with jumping knowledge networks. In ICML, 2018.
  24. Graphsmote: Imbalanced node classification on graphs with graph neural networks. In Proceedings of the 14th ACM international conference on web search and data mining, pages 833–841, 2021.
  25. To join or not to join: the illusion of privacy in social networks with mixed public and private user profiles. In Proceedings of the 18th international conference on World wide web, pages 531–540, 2009.
  26. Graph-based semi-supervised learning with nonignorable nonresponses. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, pages 7015–7025, 2019.
  27. Beyond homophily in graph neural networks: Current limitations and effective designs. NeurIPS, 2020.
  28. Graph neural networks with heterophily. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pages 11168–11176, 2021.
Citations (2)
View on Semantic Scholar

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