Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
173 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

Optimal Propagation for Graph Neural Networks (2205.02998v2)

Published 6 May 2022 in cs.LG and cs.AI

Abstract: Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input. However, the initial input graph might not be optimal in terms of specific downstream tasks, because of information scarcity, noise, adversarial attacks, or discrepancies between the distribution in graph topology, features, and groundtruth labels. In this paper, we propose a bi-level optimization approach for learning the optimal graph structure via directly learning the Personalized PageRank propagation matrix as well as the downstream semi-supervised node classification simultaneously. We also explore a low-rank approximation model for further reducing the time complexity. Empirical evaluations show the superior efficacy and robustness of the proposed model over all baseline methods.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. The political blogosphere and the 2004 us election: divided they blog. In Proceedings of the 3rd international workshop on Link discovery, pages 36–43.
  2. Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking. arXiv preprint arXiv:1707.03815.
  3. Scaling graph neural networks with approximate pagerank. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 2464–2473.
  4. Scalable graph neural networks via bidirectional propagation. arXiv preprint arXiv:2010.15421.
  5. Adaptive universal generalized pagerank graph neural network. arXiv preprint arXiv:2006.07988.
  6. Chung, F. (2007). The heat kernel as the pagerank of a graph. Proceedings of the National Academy of Sciences, 104(50):19735–19740.
  7. Cola-gnn: Cross-location attention based graph neural networks for long-term ili prediction. In Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pages 245–254.
  8. Data augmentation for deep graph learning: A survey. ACM SIGKDD Explorations Newsletter, 24(2):61–77.
  9. All you need is low (rank) defending against adversarial attacks on graphs. In Proceedings of the 13th International Conference on Web Search and Data Mining, pages 169–177.
  10. Towards scaling fully personalized pagerank: Algorithms, lower bounds, and experiments. Internet Mathematics, 2(3):333–358.
  11. Learning discrete structures for graph neural networks. In International conference on machine learning, pages 1972–1982. PMLR.
  12. Sdg: A simplified and dynamic graph neural network. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2273–2277.
  13. Predict then propagate: Graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997.
  14. Neural message passing for quantum chemistry. In International conference on machine learning, pages 1263–1272. PMLR.
  15. Graph structure learning for robust graph neural networks. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 66–74.
  16. Katz, L. (1953). A new status index derived from sociometric analysis. Psychometrika, 18(1):39–43.
  17. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  18. Diffusion improves graph learning. Advances in Neural Information Processing Systems, 32:13354–13366.
  19. Encoding social information with graph convolutional networks forpolitical perspective detection in news media. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2594–2604.
  20. Quint: on query-specific optimal networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 985–994.
  21. Personalized pagerank to a target node. arXiv preprint arXiv:1304.4658.
  22. Learning to drop: Robust graph neural network via topological denoising. In Proceedings of the 14th ACM international conference on web search and data mining, pages 779–787.
  23. Automating the construction of internet portals with machine learning. Information Retrieval, 3(2):127–163.
  24. Query-driven active surveying for collective classification. In 10th international workshop on mining and learning with graphs, volume 8, page 1.
  25. Node embedding using mutual information and self-supervision based bi-level aggregation. arXiv preprint arXiv:2104.13014.
  26. Collective classification in network data. AI magazine, 29(3):93–93.
  27. Gamenet: Graph augmented memory networks for recommending medication combination. In proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 1126–1133.
  28. Topological regularization for graph neural networks augmentation. arXiv preprint arXiv:2104.02478.
  29. Graph attention networks. arXiv preprint arXiv:1710.10903.
  30. Approximate graph propagation. arXiv preprint arXiv:2106.03058.
  31. Graph structure estimation neural networks. In Proceedings of the Web Conference 2021, pages 342–353.
  32. Fora: simple and effective approximate single-source personalized pagerank. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 505–514.
  33. Topppr: top-k personalized pagerank queries with precision guarantees on large graphs. In Proceedings of the 2018 International Conference on Management of Data, pages 441–456.
  34. Simplifying graph convolutional networks. In International conference on machine learning, pages 6861–6871. PMLR.
  35. Adversarial examples on graph data: Deep insights into attack and defense. arXiv preprint arXiv:1903.01610.
  36. Graph sanitation with application to node classification. arXiv preprint arXiv:2105.09384.
  37. Graph sanitation with application to node classification. In Proceedings of the ACM Web Conference 2022, pages 1136–1147.
  38. Optimizing classifier performance via an approximation to the wilcoxon-mann-whitney statistic. In Proceedings of the 20th international conference on machine learning (icml-03), pages 848–855.
  39. Topology optimization based graph convolutional network. In International Joint Conference on Artificial Intelligence 2019.
  40. Efficient estimation of heat kernel pagerank for local clustering. In Proceedings of the 2019 International Conference on Management of Data, pages 1339–1356.
  41. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 974–983.
  42. Beyond homophily in graph neural networks: Current limitations and effective designs. Advances in neural information processing systems, 33:7793–7804.
  43. Adversarial attacks on graph neural networks via meta learning. arXiv preprint arXiv:1902.08412.

Summary

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

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